© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71527
    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
    666
    -0.07
     options
    -0.06
    /options
    -0.06
     Zucker
    -0.06
     caval
    -0.06
     mening
    -0.06
     option
    -0.05
    866
    -0.05
     gate
    -0.05
    öz
    -0.05
    POSITIVE LOGITS
     cooling
    0.12
     recovery
    0.12
    cool
    0.11
     drying
    0.10
     cool
    0.10
     recover
    0.10
     healing
    0.10
    Cool
    0.10
     cooldown
    0.10
     recuper
    0.10
    Activations Density 0.099%

    No Known Activations