© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60224
    Prev
    Next
    INDEX
    Explanations

    ingredients and spices used in recipes

    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
    öh
    -0.07
    straction
    -0.07
    ekim
    -0.07
    oplevel
    -0.06
    abbo
    -0.06
    dbc
    -0.06
    asl
    -0.06
     sound
    -0.06
    exec
    -0.06
    oda
    -0.06
    POSITIVE LOGITS
     pow
    0.08
     powder
    0.08
     Powder
    0.07
    GROUND
    0.07
     Domin
    0.07
    ãĥĥãĥĦ
    0.07
    (pow
    0.07
     spices
    0.07
    Pow
    0.06
    pow
    0.06
    Activations Density 0.020%

    No Known Activations