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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 4-LLAMASCOPE-RES-32K
    11. 26859
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansa
    -0.16
    emsp
    -0.16
    -Allow
    -0.16
    jekt
    -0.15
    .mit
    -0.15
    iedo
    -0.15
    Venue
    -0.15
    кÑĤ
    -0.15
    afort
    -0.15
    azu
    -0.15
    POSITIVE LOGITS
    est
    0.15
    vá
    0.14
    afari
    0.14
    ugh
    0.14
     Gh
    0.14
    van
    0.14
    FR
    0.14
    abyrinth
    0.13
     Walker
    0.13
    AM
    0.13
    Activations Density 0.016%

    No Known Activations