© 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. 118673
    Prev
    Next
    INDEX
    Explanations

    programming terminology related to function parameters and return values

    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
    issen
    -0.07
     Habit
    -0.06
    anke
    -0.06
    TextEdit
    -0.06
    orno
    -0.06
    æĭĵ
    -0.06
     Newsp
    -0.06
    nergy
    -0.06
    lector
    -0.06
    quake
    -0.06
    POSITIVE LOGITS
    ç°
    0.07
     Sai
    0.07
    Coder
    0.07
     Caucus
    0.06
     Kok
    0.06
    .Generated
    0.06
     Prest
    0.06
    ipar
    0.06
    eyJ
    0.06
    ROP
    0.06
    Activations Density 0.002%

    No Known Activations