© 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. 123812
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numerical values that signify structure in the text

    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
    廳
    -0.06
    éĻ½
    -0.06
    621
    -0.06
     heapq
    -0.06
     Hooks
    -0.06
    olution
    -0.06
    _PI
    -0.06
     æĵ
    -0.06
    еÑĤÑĮ
    -0.06
     defaultMessage
    -0.06
    POSITIVE LOGITS
    PAIR
    0.06
     Wilkinson
    0.06
    sig
    0.06
    anden
    0.06
    .getPage
    0.06
    argent
    0.06
    mÃŃ
    0.06
    keit
    0.06
    kit
    0.06
    EB
    0.06
    Activations Density 0.001%

    No Known Activations