Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5338
    Prev
    Next
    INDEX
    Explanations

    references to the purpose or intended use of content

    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
    iddy
    -0.07
     acc
    -0.06
    end
    -0.06
    136
    -0.06
     sac
    -0.06
    ITOR
    -0.06
     Hra
    -0.06
    ards
    -0.05
     gon
    -0.05
    y
    -0.05
    POSITIVE LOGITS
    rk
    0.07
    TouchUpInside
    0.07
    ibu
    0.07
    GMEM
    0.07
    覧
    0.07
    zeigen
    0.07
     showc
    0.07
    ergus
    0.07
    /Dk
    0.07
    RunLoop
    0.07
    Activations Density 0.003%

    No Known Activations