Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57397
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and preparation details

    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
     Tank
    -0.08
     tank
    -0.07
    azo
    -0.07
     Iss
    -0.07
     Chain
    -0.07
    urtle
    -0.06
    ìĸ¼
    -0.06
    oop
    -0.06
     chain
    -0.06
     tanks
    -0.06
    POSITIVE LOGITS
     oven
    0.08
     baking
    0.08
     nude
    0.08
     bake
    0.08
     naked
    0.07
     Spread
    0.07
    çĥ
    0.07
    çĦ¼
    0.07
    773
    0.07
    oven
    0.07
    Activations Density 0.069%

    No Known Activations