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. 22-LLAMASCOPE-RES-131K
    6. 5727
    Prev
    Next
    INDEX
    Explanations

    terms related to biological studies and collections

    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
    zzo
    -0.06
     rats
    -0.06
     beef
    -0.06
     birds
    -0.06
    oken
    -0.06
     bulls
    -0.06
    indle
    -0.06
    γÏĩ
    -0.06
    .shtml
    -0.06
     hire
    -0.06
    POSITIVE LOGITS
     cater
    0.17
     Cater
    0.15
     butterfly
    0.13
     butterflies
    0.13
     monarch
    0.13
     Butterfly
    0.13
     Butter
    0.12
     silk
    0.10
     butter
    0.10
     lar
    0.10
    Activations Density 0.041%

    No Known Activations