© 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. 15-LLAMASCOPE-RES-131K
    11. 89964
    Prev
    Next
    INDEX
    Explanations

    references to athlete performances and statistics

    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
    eref
    -0.07
    ocument
    -0.07
    abouts
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    ston
    -0.07
    Zend
    -0.07
    Lead
    -0.07
    udd
    -0.07
    ontrol
    -0.07
    jure
    -0.07
    POSITIVE LOGITS
     whose
    0.08
    907
    0.06
     whom
    0.06
    lic
    0.06
     who
    0.06
    .Stack
    0.06
     key
    0.06
     active
    0.06
     quantity
    0.06
     Qu
    0.06
    Activations Density 0.030%

    No Known Activations