© 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. 116634
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to programming or server errors

    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
    одо
    -0.08
    engin
    -0.08
    utterstock
    -0.07
    _INLINE
    -0.07
    ãĥģãĥ¥
    -0.07
    .GraphicsUnit
    -0.07
    okit
    -0.07
    .jasper
    -0.07
    ynes
    -0.07
    .cx
    -0.07
    POSITIVE LOGITS
    ếp
    0.06
    .study
    0.06
    icopt
    0.06
    noinspection
    0.06
    296
    0.06
    kovÄĽ
    0.06
    cassert
    0.06
    GB
    0.06
    _SR
    0.05
    itel
    0.05
    Activations Density 0.019%

    No Known Activations