© 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. 76397
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "blank" and its variations in different contexts

    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
    ÌĨ
    -0.08
    antas
    -0.08
    istic
    -0.07
    ylko
    -0.07
    jmp
    -0.07
    naments
    -0.07
    inality
    -0.07
    faq
    -0.07
    ussy
    -0.07
    annis
    -0.07
    POSITIVE LOGITS
    eting
    0.12
    eted
    0.11
     slate
    0.09
    aded
    0.07
    enburg
    0.07
    enstein
    0.07
    /null
    0.07
    ishments
    0.06
     Slate
    0.06
    arf
    0.06
    Activations Density 0.004%

    No Known Activations