© 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. 82533
    Prev
    Next
    INDEX
    Explanations

    attributes of a player's performance and value to their team

    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
    otti
    -0.07
    Bold
    -0.07
    rowsable
    -0.07
    lÃŃÄį
    -0.06
    IOR
    -0.06
    libc
    -0.06
    isku
    -0.06
     Bounty
    -0.06
    angl
    -0.06
    scriptId
    -0.06
    POSITIVE LOGITS
     underrated
    0.09
     CONTRIBUT
    0.08
     contribution
    0.07
    leta
    0.07
     bridges
    0.07
     Contribution
    0.07
     brid
    0.07
     versatility
    0.07
     reliable
    0.07
     contrib
    0.07
    Activations Density 0.043%

    No Known Activations