© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83807
    Prev
    Next
    INDEX
    Explanations

    technical terms and commands related to file handling and system operations in programming

    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
     buflen
    -0.06
    dex
    -0.06
    utt
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    æİ¨
    -0.06
     tez
    -0.06
     CEL
    -0.06
     wid
    -0.06
    izen
    -0.06
     Widow
    -0.06
    POSITIVE LOGITS
    ENER
    0.07
    è¯ķ
    0.07
     ford
    0.07
    erot
    0.06
    .Env
    0.06
    .Interop
    0.06
    quine
    0.06
    UNDLE
    0.06
    <decimal
    0.06
    út
    0.06
    Activations Density 0.020%

    No Known Activations