Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16537
    Prev
    Next
    INDEX
    Explanations

    references to various types of professional sports contracts and related terms

    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
    å¼ı
    -0.07
    ikk
    -0.07
    -hooks
    -0.07
    {\"
    -0.07
    окон
    -0.06
    soever
    -0.06
    [email
    -0.06
    κι
    -0.06
     Sür
    -0.06
    %C
    -0.06
    POSITIVE LOGITS
    bie
    0.07
    364
    0.07
    492
    0.07
    458
    0.06
    .infinity
    0.06
    -fontawesome
    0.06
    /widgets
    0.06
    ãĤ¦ãĥ³
    0.06
     pager
    0.06
    ets
    0.06
    Activations Density 0.022%

    No Known Activations