© 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. 5-LLAMASCOPE-RES-131K
    11. 126149
    Prev
    Next
    INDEX
    Explanations

    references to food, particularly in relation to preparation, categorization, and qualities of ingredients

    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
     Banc
    -0.08
    ¼åIJĪ
    -0.06
    erk
    -0.06
    alytics
    -0.06
    ystore
    -0.06
    Release
    -0.06
    gens
    -0.06
    lessly
    -0.06
    bh
    -0.06
    ario
    -0.06
    POSITIVE LOGITS
     oku
    0.08
    enza
    0.07
    ennen
    0.07
    utherford
    0.07
    imar
    0.07
    inus
    0.07
     smr
    0.07
    ;o
    0.07
    ForRow
    0.07
    Msp
    0.06
    Activations Density 0.424%

    No Known Activations