© 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. 28983
    Prev
    Next
    INDEX
    Explanations

    mentions of the artist Rothko

    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
    uali
    -0.08
    ãĥ¬ãĥĥãĥĪ
    -0.07
    ature
    -0.07
    nown
    -0.07
    utom
    -0.07
    untime
    -0.07
    pending
    -0.07
    uality
    -0.07
    Interop
    -0.07
    ually
    -0.07
    POSITIVE LOGITS
    stein
    0.08
    kop
    0.07
    tej
    0.07
    childs
    0.07
    este
    0.07
    eg
    0.06
    well
    0.06
    thora
    0.06
     mild
    0.06
    unos
    0.06
    Activations Density 0.002%

    No Known Activations