© 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. 9-LLAMASCOPE-RES-131K
    11. 95567
    Prev
    Next
    INDEX
    Explanations

    references to the Marvel Cinematic Universe and its associated films

    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
    igen
    -0.07
    onas
    -0.07
    okt
    -0.07
    LError
    -0.06
    ailability
    -0.06
    488
    -0.06
    /fw
    -0.06
    aks
    -0.06
    eprom
    -0.06
    oner
    -0.06
    POSITIVE LOGITS
    idores
    0.07
    decorators
    0.07
    aravel
    0.06
    RefCount
    0.06
     Mour
    0.06
    OfType
    0.06
    ousel
    0.06
    unic
    0.06
    .documentation
    0.06
    ropol
    0.06
    Activations Density 0.000%

    No Known Activations