© 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. 87724
    Prev
    Next
    INDEX
    Explanations

    instances of writing and related 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
    woff
    -0.08
    .extensions
    -0.08
    ÃŃrk
    -0.07
    avir
    -0.07
    kul
    -0.07
    ầy
    -0.07
    -lfs
    -0.07
    ondo
    -0.07
     é¤
    -0.07
    fab
    -0.07
    POSITIVE LOGITS
     about
    0.07
     articles
    0.07
    eller
    0.06
    oton
    0.06
    é¡¿
    0.06
    ragon
    0.06
     Articles
    0.06
     columns
    0.06
     for
    0.05
     industrial
    0.05
    Activations Density 0.011%

    No Known Activations