© 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. 83176
    Prev
    Next
    INDEX
    Explanations

    references to historical and geographical subjects

    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
    áv
    -0.07
    .LookAndFeel
    -0.07
     Vance
    -0.06
    ë¹Į
    -0.06
    Illustr
    -0.06
     *,↵
    -0.06
    -eslint
    -0.06
    741
    -0.06
    Âį
    -0.06
    ickerView
    -0.06
    POSITIVE LOGITS
     http
    0.08
    ï¼ĮåŃĺäºİ
    0.08
     https
    0.08
    åŃĺäºİ
    0.08
     Wayback
    0.07
    :http
    0.07
    rray
    0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
     YouTube
    0.07
     www
    0.07
    Activations Density 0.028%

    No Known Activations