© 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. 129183
    Prev
    Next
    INDEX
    Explanations

    historical dates 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
    apan
    -0.06
    _span
    -0.06
     Ow
    -0.06
    acak
    -0.06
     Furn
    -0.06
    aca
    -0.06
    adla
    -0.06
     Tal
    -0.06
    pute
    -0.06
    atter
    -0.06
    POSITIVE LOGITS
    ISC
    0.07
    RTL
    0.07
     Verfüg
    0.07
    خت
    0.07
    ulum
    0.07
    cheid
    0.06
    oksen
    0.06
    ;!
    0.06
    Ø
    0.06
     Lover
    0.06
    Activations Density 0.055%

    No Known Activations