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

    Neuronpedia

    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. 18773
    Prev
    Next
    INDEX
    Explanations

    terms related to commercial entities and legal classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    erties
    -0.17
    kest
    -0.16
    (equalTo
    -0.14
    ologia
    -0.14
    alyzer
    -0.14
    ologie
    -0.14
     nieu
    -0.14
    ±Ð¾ÑĤ
    -0.14
    ène
    -0.13
     Anthrop
    -0.13
    POSITIVE LOGITS
    ational
    0.46
    acional
    0.43
    ional
    0.40
    inal
    0.38
    ATIONAL
    0.37
    ential
    0.35
    itional
    0.34
    onal
    0.32
    itational
    0.30
    essional
    0.29
    Activations Density 0.153%

    No Known Activations