© 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. 40152
    Prev
    Next
    INDEX
    Explanations

    references to events and gatherings

    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
    å³
    -0.07
    asurer
    -0.07
    ê°ĢìļĶ
    -0.06
    reau
    -0.06
    atura
    -0.06
    ê·ł
    -0.06
     incel
    -0.06
    opsis
    -0.06
    oggles
    -0.06
    ampions
    -0.06
    POSITIVE LOGITS
    ινη
    0.07
    abajo
    0.07
     our
    0.07
     +
    0.06
     we
    0.06
    ngine
    0.06
    omik
    0.06
    mÃŃt
    0.06
    ahn
    0.06
    evin
    0.06
    Activations Density 0.002%

    No Known Activations