© 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. 82600
    Prev
    Next
    INDEX
    Explanations

    references to sports team management decisions or player acquisitions

    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
    etes
    -0.08
    neutral
    -0.08
    MethodInfo
    -0.07
    ادÙĦ
    -0.07
    Ń
    -0.07
    astered
    -0.07
    tie
    -0.07
    annes
    -0.07
    xCD
    -0.07
    istrovstvÃŃ
    -0.07
    POSITIVE LOGITS
     addition
    0.08
     additions
    0.07
     top
    0.06
    upo
    0.06
    uto
    0.06
     competition
    0.06
    ummer
    0.06
    itan
    0.06
    antry
    0.06
     thin
    0.06
    Activations Density 0.020%

    No Known Activations