© 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. 126438
    Prev
    Next
    INDEX
    Explanations

    components and actions related to cooking processes

    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
    oda
    -0.07
    asel
    -0.07
    vault
    -0.07
    plex
    -0.07
    alat
    -0.07
    stad
    -0.07
    erva
    -0.07
    ayne
    -0.07
    anta
    -0.06
    inka
    -0.06
    POSITIVE LOGITS
     enc
    0.07
     dred
    0.07
    Mappings
    0.07
     electro
    0.06
     glove
    0.06
     MACHINE
    0.06
    BIN
    0.06
     battered
    0.06
     Venice
    0.06
    (Binary
    0.06
    Activations Density 0.039%

    No Known Activations