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. 43389
    Prev
    Next
    INDEX
    Explanations

    names of individuals and related biographical details

    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
     OMAP
    -0.07
    Verdana
    -0.07
    ião
    -0.07
    Sean
    -0.07
    '=>['
    -0.07
    amble
    -0.07
    Ao
    -0.07
     Quang
    -0.07
    Calibri
    -0.07
    Yii
    -0.07
    POSITIVE LOGITS
     Cohen
    0.15
     Friedman
    0.15
     Levine
    0.14
     Goldberg
    0.14
     Katz
    0.14
    owitz
    0.14
     Goldman
    0.14
     Epstein
    0.14
     Weinstein
    0.14
     Levin
    0.14
    Activations Density 0.129%

    No Known Activations