© 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. 119105
    Prev
    Next
    INDEX
    Explanations

    references to entertainment, especially related to film and music

    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
    fty
    -0.07
    irse
    -0.07
    çĦ¶
    -0.07
    314
    -0.06
    edReader
    -0.06
    617
    -0.06
    cco
    -0.06
     Mattis
    -0.06
    ELLOW
    -0.06
    orate
    -0.06
    POSITIVE LOGITS
     Houston
    0.07
    ilor
    0.07
    Houston
    0.07
     Walters
    0.06
     substance
    0.06
     Pars
    0.06
     chart
    0.06
     NOI
    0.06
    ghan
    0.06
    .monitor
    0.06
    Activations Density 0.001%

    No Known Activations