© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26858
    Prev
    Next
    INDEX
    Explanations

    code-related variables and functions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     dlg
    -0.06
    _parms
    -0.06
     folks
    -0.06
    ixels
    -0.06
     biz
    -0.06
    azar
    -0.06
    captures
    -0.06
    xa
    -0.06
    recision
    -0.06
    omon
    -0.06
    POSITIVE LOGITS
     derp
    0.09
    )((((
    0.07
    afort
    0.07
     nedok
    0.07
     Structures
    0.07
     ãĥ¾
    0.06
     Discord
    0.06
     spear
    0.06
    åĤ¨
    0.06
    ~-~-
    0.06
    Activations Density 0.052%

    No Known Activations