© 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. 78820
    Prev
    Next
    INDEX
    Explanations

    references to artistic and cultural communities

    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
    atak
    -0.07
     pathMatch
    -0.07
    PIO
    -0.07
    redd
    -0.07
    ToLocal
    -0.07
    ανά
    -0.07
    cken
    -0.07
    коп
    -0.07
     ÑĥлÑĥÑĩ
    -0.06
    leigh
    -0.06
    POSITIVE LOGITS
     via
    0.08
     cul
    0.07
    via
    0.07
    such
    0.07
     represented
    0.06
     tslib
    0.06
     led
    0.06
     such
    0.06
     courtesy
    0.06
     starting
    0.06
    Activations Density 0.061%

    No Known Activations