© 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. 15-LLAMASCOPE-RES-131K
    11. 27015
    Prev
    Next
    INDEX
    Explanations

    references to the UN General Assembly and its activities

    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
    loh
    -0.07
    oine
    -0.06
    iete
    -0.06
     nationwide
    -0.06
     winning
    -0.06
    iena
    -0.06
    asz
    -0.06
    CoreApplication
    -0.05
    cola
    -0.05
    452
    -0.05
    POSITIVE LOGITS
    uguay
    0.07
     session
    0.07
     deleg
    0.07
    atin
    0.07
     Quad
    0.07
    /Framework
    0.07
    afen
    0.07
    BuilderFactory
    0.07
     Prec
    0.07
    ChangedEventArgs
    0.07
    Activations Density 0.003%

    No Known Activations