Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43917
    Prev
    Next
    INDEX
    Explanations

    names of well-known public figures and references to popular culture

    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
    ãĥĥãĤ·ãĥ¥
    -0.08
    ürn
    -0.07
     itself
    -0.07
     оÑĢганов
    -0.07
    IPH
    -0.07
    SEL
    -0.07
    venue
    -0.07
    tiler
    -0.07
    ucken
    -0.07
    onta
    -0.07
    POSITIVE LOGITS
    -led
    0.12
    ’s
    0.12
    's
    0.12
    /J
    0.11
    ‘s
    0.10
    -approved
    0.10
    /K
    0.10
    -designed
    0.09
    -directed
    0.09
    /P
    0.09
    Activations Density 0.046%

    No Known Activations