© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97264
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to software and data processing

    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
    ubi
    -0.07
    endale
    -0.06
     mim
    -0.06
    ÙĪÙĨÙĬ
    -0.06
    baum
    -0.06
    oose
    -0.06
    uard
    -0.06
     MPS
    -0.06
     Independ
    -0.06
    gia
    -0.06
    POSITIVE LOGITS
    peq
    0.07
    agnitude
    0.06
    afia
    0.06
    çIJ³
    0.06
    گاÙĩ
    0.06
    rophe
    0.06
    :\/\/
    0.06
     (![
    0.06
    fragment
    0.06
    .ArgumentParser
    0.06
    Activations Density 0.034%

    No Known Activations