© 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. 70989
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking and preparation steps

    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
     Sob
    -0.06
     Rum
    -0.06
     Freedom
    -0.06
     valid
    -0.06
    ardo
    -0.06
     Dil
    -0.06
     copies
    -0.06
    awe
    -0.06
     formal
    -0.05
     copy
    -0.05
    POSITIVE LOGITS
    .Interop
    0.08
    elpers
    0.08
    setLabel
    0.08
     Infragistics
    0.08
    /stdc
    0.07
    using
    0.07
     fkk
    0.07
    TEGER
    0.07
     vess
    0.07
    antage
    0.07
    Activations Density 0.002%

    No Known Activations