© 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. 82555
    Prev
    Next
    INDEX
    Explanations

    positive attributes related to individuals' contributions and achievements within their community or school

    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
    ãĤ¿ãĥ³
    -0.07
     å¹
    -0.07
    uels
    -0.07
    ấu
    -0.07
    opsis
    -0.06
     uncert
    -0.06
    prak
    -0.06
    lund
    -0.06
    (IServiceCollection
    -0.06
     sinh
    -0.06
    POSITIVE LOGITS
     reputation
    0.10
     credit
    0.08
     reput
    0.08
     Reputation
    0.08
     embarrassment
    0.08
    credit
    0.07
     discredit
    0.07
     shame
    0.06
     Carry
    0.06
     represent
    0.06
    Activations Density 0.033%

    No Known Activations