© 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. 29604
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking and food preparation

    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
     gamm
    -0.07
    ernational
    -0.07
    ispens
    -0.06
    -export
    -0.06
    rij
    -0.06
     Farrell
    -0.06
     Daniels
    -0.06
    ανά
    -0.06
    anmar
    -0.06
    redd
    -0.06
    POSITIVE LOGITS
     Pocket
    0.07
    UGH
    0.07
    uw
    0.07
     Moor
    0.07
    Pocket
    0.06
    etak
    0.06
     during
    0.06
     pocket
    0.06
     During
    0.06
     durante
    0.06
    Activations Density 0.030%

    No Known Activations