© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 85937
    Prev
    Next
    INDEX
    Explanations

    content related to search query syntax and Boolean logic operations

    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
    EMA
    -0.07
    oppable
    -0.06
    ovit
    -0.06
    .swap
    -0.06
    kud
    -0.06
    .metro
    -0.06
     tear
    -0.06
    accent
    -0.06
    suma
    -0.06
     channels
    -0.06
    POSITIVE LOGITS
    -results
    0.07
     prelim
    0.07
     Results
    0.07
    ICO
    0.07
    rrha
    0.07
     results
    0.07
    Results
    0.06
    ÙĪÙĨØ©
    0.06
    _RESERVED
    0.06
    pipes
    0.06
    Activations Density 0.016%

    No Known Activations