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. 44198
    Prev
    Next
    INDEX
    Explanations

    terms related to financial policies and support for small businesses

    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
    ropp
    -0.07
    ici
    -0.07
    okens
    -0.07
    .va
    -0.07
    _hint
    -0.07
    DBNull
    -0.07
    illes
    -0.07
     pipes
    -0.07
    ereum
    -0.07
     Hull
    -0.07
    POSITIVE LOGITS
     frank
    0.10
     assess
    0.09
     BAS
    0.09
     fringe
    0.09
     lod
    0.08
     super
    0.08
     Division
    0.08
     Lod
    0.07
     Inst
    0.07
     CG
    0.07
    Activations Density 0.010%

    No Known Activations