Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5761
    Prev
    Next
    INDEX
    Explanations

    references to governmental or official entities and their roles

    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
    +-
    -0.06
    itel
    -0.06
    èī¯
    -0.06
     Weaver
    -0.06
    شت
    -0.06
     ÑĦÑĥнда
    -0.06
    ifr
    -0.06
     Gregg
    -0.06
    SED
    -0.06
     Peg
    -0.06
    POSITIVE LOGITS
     Ministry
    0.08
     Border
    0.07
     Hey
    0.07
     ministry
    0.07
    formatter
    0.07
     border
    0.06
     Ros
    0.06
    è¡
    0.06
     higher
    0.06
     Federal
    0.06
    Activations Density 0.010%

    No Known Activations