© 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 EvalsExportsinterp-engineNEWAPI 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. 92667
    Prev
    Next
    INDEX
    Explanations

    statements about the nature and utility of anonymous functions in programming

    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
    ledi
    -0.07
    -icons
    -0.06
    IgnoreCase
    -0.06
    bum
    -0.06
    xad
    -0.06
    din
    -0.06
    -caption
    -0.06
    æĭľ
    -0.06
     property
    -0.06
     Ik
    -0.06
    POSITIVE LOGITS
    cean
    0.07
    opp
    0.07
     durumlarda
    0.07
    å¼¥
    0.07
     occasions
    0.07
    _BC
    0.07
    è¡Ľ
    0.06
    ÑİÑĢ
    0.06
    .sprite
    0.06
    .comp
    0.06
    Activations Density 0.011%

    No Known Activations