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. 43938
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Published" in different contexts

    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
    /goto
    -0.07
    _DIRECTION
    -0.07
    .freeze
    -0.07
     treff
    -0.07
    requete
    -0.06
    achuset
    -0.06
    Ỽp
    -0.06
    _FINISH
    -0.06
    ECTOR
    -0.06
     èĩªåĬ¨çĶŁæĪIJ
    -0.06
    POSITIVE LOGITS
    duration
    0.06
     Clinical
    0.06
     sco
    0.06
    ↵
    0.06
     Papers
    0.06
    es
    0.06
    bib
    0.06
     Abstract
    0.06
    ↵↵
    0.06
     Article
    0.06
    Activations Density 0.004%

    No Known Activations