© 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. 40341
    Prev
    Next
    INDEX
    Explanations

    cooking-related terms and instructions

    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
    ضر
    -0.07
     Wine
    -0.06
     contingency
    -0.06
    iba
    -0.06
     Resolution
    -0.06
    orig
    -0.06
     pickup
    -0.06
    ãģijãģªãģĦ
    -0.06
     jars
    -0.06
    Ïĥη
    -0.06
    POSITIVE LOGITS
     pancakes
    0.08
     breakfast
    0.08
    strup
    0.08
     batter
    0.08
     morning
    0.07
    inton
    0.07
     Breakfast
    0.07
    .Flat
    0.07
     Platt
    0.07
    -flat
    0.07
    Activations Density 0.009%

    No Known Activations