© 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. 118563
    Prev
    Next
    INDEX
    Explanations

    references to specific events or actions related to character development and interactions

    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
     lately
    -0.08
     recently
    -0.08
    opsis
    -0.07
     currently
    -0.07
    à¸Ĥà¸ĵะ
    -0.07
     recent
    -0.07
     Interrupt
    -0.07
    Interrupt
    -0.07
    unate
    -0.06
    grave
    -0.06
    POSITIVE LOGITS
     immediately
    0.08
     became
    0.07
    éĸ
    0.07
     immedi
    0.07
     becomes
    0.07
     become
    0.07
     continue
    0.06
     STILL
    0.06
     proceeded
    0.06
     continues
    0.06
    Activations Density 0.094%

    No Known Activations