© 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. 121246
    Prev
    Next
    INDEX
    Explanations

    references to academic achievements and sports-related accomplishments

    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
    elle
    -0.09
    idge
    -0.07
    IDGE
    -0.07
     Shields
    -0.07
    ÅĻÃŃž
    -0.06
    eyim
    -0.06
     "}
    -0.06
    ãģĿãģĵ
    -0.06
     Admir
    -0.06
     aile
    -0.06
    POSITIVE LOGITS
    _ABORT
    0.07
    otes
    0.06
    ymoon
    0.06
    annels
    0.06
     came
    0.06
    EV
    0.06
    969
    0.06
    ogh
    0.06
     switch
    0.05
    mic
    0.05
    Activations Density 0.011%

    No Known Activations