© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 21336
    Prev
    Next
    INDEX
    Explanations

    instances of the word "As" and its variations, indicating it is identifying conditional or contextual statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "As" when it introduces a statement of identity, role, or perspective (e.g., "As a company," "As faculty," "As members").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    sentence-initial subordinating conjunctions that introduce a dependent clause.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tra
    -0.17
    111
    -0.16
     gangs
    -0.14
    var
    -0.14
    309
    -0.14
    entina
    -0.14
    12
    -0.14
    074
    -0.14
    errat
    -0.13
    123
    -0.13
    POSITIVE LOGITS
     cust
    0.18
    ersh
    0.18
     caret
    0.18
     stew
    0.17
    usta
    0.16
     báºŃc
    0.16
    .scalablytyped
    0.15
     citiz
    0.15
    /Dk
    0.15
     humans
    0.15
    Activations Density 0.071%

    No Known Activations