© 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. 79881
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or amusing situations during social interactions

    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
     gymn
    -0.07
    oled
    -0.07
     bottle
    -0.07
     Ballet
    -0.07
    è¸
    -0.07
     Bottle
    -0.06
     urban
    -0.06
     ballet
    -0.06
    åªĴ
    -0.06
    oton
    -0.06
    POSITIVE LOGITS
     tournament
    0.08
    spi
    0.07
     tournaments
    0.07
     rake
    0.07
     Tournament
    0.07
    âĻł
    0.07
     banker
    0.07
    itaire
    0.07
     Poker
    0.06
    fdf
    0.06
    Activations Density 0.026%

    No Known Activations