© 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. 84427
    Prev
    Next
    INDEX
    Explanations

    references to people and their knowledge or expertise

    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
    asar
    -0.08
    USH
    -0.07
    .FontStyle
    -0.07
    anca
    -0.07
    ëħIJ
    -0.06
    anel
    -0.06
    IMIT
    -0.06
    CallCheck
    -0.06
    eneric
    -0.06
    .GetSize
    -0.06
    POSITIVE LOGITS
     expertise
    0.09
     know
    0.08
     knows
    0.08
     knowledge
    0.07
     knowing
    0.07
     promising
    0.07
    799
    0.07
     capable
    0.06
     potentially
    0.06
     ÙĦدÙĬ
    0.06
    Activations Density 0.033%

    No Known Activations