© 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. 5640
    Prev
    Next
    INDEX
    Explanations

    references to different types of data, methods, and models used in scientific or research contexts

    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
    ogui
    -0.07
    plr
    -0.07
    oplay
    -0.07
    мп
    -0.07
    ections
    -0.07
    udur
    -0.07
    ectl
    -0.06
     Alive
    -0.06
    udu
    -0.06
     Å¡p
    -0.06
    POSITIVE LOGITS
     versus
    0.34
     vs
    0.33
     Vs
    0.25
    vs
    0.24
    _vs
    0.24
     compared
    0.23
    -vs
    0.23
     Vers
    0.18
    -vers
    0.18
     VS
    0.17
    Activations Density 0.148%

    No Known Activations