© 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. 74838
    Prev
    Next
    INDEX
    Explanations

    references to luxury food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names, specialized terms, and distinctive words that serve as key identifiers in various domains like cooking ingredients, proper names, technical notations, or foreign language expressions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Å¡tÄĽ
    -0.08
    lio
    -0.07
    shed
    -0.07
    ÃľRK
    -0.07
    urge
    -0.07
    049
    -0.07
    /Add
    -0.07
    à¥Ģय
    -0.07
    ¦æĥħ
    -0.06
    rais
    -0.06
    POSITIVE LOGITS
    ness
    0.08
    Ù
    0.08
    eniable
    0.08
    nown
    0.08
    etail
    0.08
    naments
    0.07
    igator
    0.07
    áÄį
    0.07
    NESS
    0.07
    egral
    0.07
    Activations Density 0.117%

    No Known Activations