© 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. 94025
    Prev
    Next
    INDEX
    Explanations

    references to political or governmental structures and events

    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
     Dynasty
    -0.08
    versed
    -0.06
    lector
    -0.06
     Planet
    -0.06
    VED
    -0.06
     Dy
    -0.06
    anio
    -0.06
    @mail
    -0.06
     dynasty
    -0.06
     Dyn
    -0.06
    POSITIVE LOGITS
     âĹĦ
    0.07
     createAction
    0.07
    lix
    0.06
    entai
    0.06
    à¤ķरण
    0.06
    acker
    0.06
     session
    0.06
    umd
    0.06
    asaki
    0.06
    stay
    0.06
    Activations Density 0.053%

    No Known Activations