© 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. 125803
    Prev
    Next
    INDEX
    Explanations

    historical figures and events related to colonization

    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
    å±Ĭ
    -0.07
    uevo
    -0.06
    rof
    -0.06
    /self
    -0.06
     Feed
    -0.06
     Corinth
    -0.06
    .Design
    -0.06
    ãģĭãģ£ãģ¦
    -0.06
    ergus
    -0.06
    announce
    -0.06
    POSITIVE LOGITS
     Native
    0.08
     Indian
    0.07
    Native
    0.07
    actus
    0.07
     Circ
    0.07
     native
    0.07
    _NATIVE
    0.07
    /native
    0.06
     subs
    0.06
     Indians
    0.06
    Activations Density 0.003%

    No Known Activations