© 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. 17-LLAMASCOPE-RES-131K
    11. 71107
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" within various 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
    ÈĽi
    -0.07
    é»ĺ
    -0.07
    ضة
    -0.07
    uro
    -0.06
    ova
    -0.06
    .nih
    -0.06
    ovo
    -0.06
    èĨ
    -0.06
    ovÄĽ
    -0.06
    allen
    -0.06
    POSITIVE LOGITS
     remarks
    0.08
    487
    0.08
     remark
    0.08
     comments
    0.08
     talk
    0.08
     reply
    0.07
    tod
    0.07
     letter
    0.07
    remarks
    0.07
     statement
    0.07
    Activations Density 0.048%

    No Known Activations