© 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. 70961
    Prev
    Next
    INDEX
    Explanations

    URL patterns and references to web resources

    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
    mitt
    -0.06
     pres
    -0.06
    enti
    -0.06
    agen
    -0.06
    annes
    -0.06
    entai
    -0.06
     blindness
    -0.06
    andel
    -0.06
    ÅĻes
    -0.06
    entar
    -0.06
    POSITIVE LOGITS
     badge
    0.08
     Mature
    0.07
    badge
    0.07
     seal
    0.07
    -badge
    0.07
    CEF
    0.07
     badges
    0.07
    .market
    0.07
     Badge
    0.07
    DEVICE
    0.07
    Activations Density 0.002%

    No Known Activations