© 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. 15546
    Prev
    Next
    INDEX
    Explanations

    references to mathematical theories and concepts related to problem-solving

    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
    çĬ¯
    -0.06
     discount
    -0.06
     sculpt
    -0.06
     discounts
    -0.06
    fout
    -0.06
    ominator
    -0.06
     bout
    -0.06
    ounder
    -0.06
     commits
    -0.06
    rostÅĻed
    -0.06
    POSITIVE LOGITS
    INGER
    0.07
    elerik
    0.07
    SGlobal
    0.07
    ecedor
    0.07
     interpol
    0.07
    ød
    0.07
    .misc
    0.07
    åIJĪåIJĮ
    0.06
    ëįķ
    0.06
     TMPro
    0.06
    Activations Density 0.038%

    No Known Activations