© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77506
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" and related sequences in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avers
    -0.08
    stry
    -0.07
    eldorf
    -0.07
    ãĥ¬ãĥ¼
    -0.06
    ellant
    -0.06
    raya
    -0.06
    à¥įथ
    -0.06
     Basket
    -0.06
    hed
    -0.06
    geois
    -0.06
    POSITIVE LOGITS
    onen
    0.07
     bufsize
    0.07
    698
    0.07
     наг
    0.07
    enaire
    0.06
    nonnull
    0.06
    ToEnd
    0.06
    onic
    0.06
    cona
    0.06
    /all
    0.06
    Activations Density 0.011%

    No Known Activations