© 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. 126926
    Prev
    Next
    INDEX
    Explanations

    logging and error handling functions in code

    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
    readcr
    -0.07
    amin
    -0.07
    illard
    -0.07
    ramer
    -0.06
    .execSQL
    -0.06
    hem
    -0.06
    Ì
    -0.06
    amd
    -0.06
    lette
    -0.06
    inki
    -0.06
    POSITIVE LOGITS
    chia
    0.07
    _ln
    0.06
     Clyde
    0.06
    datatable
    0.06
    ahlen
    0.06
    OffsetTable
    0.06
     ç§ĭ
    0.06
    ÏīÏĤ
    0.06
     omas
    0.06
     getClass
    0.06
    Activations Density 0.001%

    No Known Activations