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. 43631
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases and criminal accusations

    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
    DH
    -0.07
     Morav
    -0.06
    Marco
    -0.06
     lah
    -0.06
     Newfoundland
    -0.06
    ãĥ«ãĥķ
    -0.06
     Norwich
    -0.06
     Leban
    -0.06
    dux
    -0.06
     Marco
    -0.06
    POSITIVE LOGITS
     Kelly
    0.14
     Chicago
    0.13
     Cook
    0.12
     Illinois
    0.11
    Chicago
    0.11
    Kelly
    0.11
     Lifetime
    0.11
    Cook
    0.10
     chicago
    0.10
     Surv
    0.10
    Activations Density 0.008%

    No Known Activations