© 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. 5107
    Prev
    Next
    INDEX
    Explanations

    descriptions of atmospheric and aesthetic elements in settings

    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
     sog
    -0.06
     Belt
    -0.06
    _yaw
    -0.05
    DT
    -0.05
     Legendary
    -0.05
     {(
    -0.05
    oe
    -0.05
     vests
    -0.05
    ivers
    -0.05
    xca
    -0.05
    POSITIVE LOGITS
    YRO
    0.08
    OfString
    0.07
     moden
    0.07
    راÙĤ
    0.07
    COPE
    0.07
    .bz
    0.07
     trees
    0.07
    bé
    0.07
    yor
    0.07
    HEME
    0.07
    Activations Density 0.031%

    No Known Activations