© 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. 38463
    Prev
    Next
    INDEX
    Explanations

    references to specific criteria, awards, and guidelines within various contexts

    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
    olders
    -0.07
    _perf
    -0.06
    ously
    -0.06
    ldkf
    -0.06
    raud
    -0.06
    ifu
    -0.06
     Praha
    -0.06
     sag
    -0.06
    kov
    -0.06
     polož
    -0.06
    POSITIVE LOGITS
     target
    0.08
     focus
    0.07
    FORMAT
    0.07
     TMPro
    0.07
    èĮĥåĽ´
    0.07
     targeted
    0.07
    _focus
    0.07
     targets
    0.07
     range
    0.07
    -target
    0.07
    Activations Density 0.031%

    No Known Activations