© 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. 15-LLAMASCOPE-RES-131K
    11. 103951
    Prev
    Next
    INDEX
    Explanations

    references to celebrities and notable figures

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

    Names of celebrities, cultural icons, and widely recognized public figures that appear in media, entertainment, or cultural discussions.

    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
    lessly
    -0.09
    uso
    -0.07
    sep
    -0.07
    (er
    -0.07
    usc
    -0.06
    amac
    -0.06
    858
    -0.06
    CE
    -0.06
    aday
    -0.06
    ape
    -0.06
    POSITIVE LOGITS
    ian
    0.10
    -Benz
    0.08
    -esque
    0.07
    izzato
    0.07
    ium
    0.07
    lla
    0.07
    .gov
    0.07
     dioxide
    0.07
    že
    0.07
    .gdx
    0.07
    Activations Density 0.045%

    No Known Activations