© 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. 14236
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éłĺ
    -0.06
    eree
    -0.06
    itore
    -0.06
    glob
    -0.06
    TODO
    -0.06
     pcb
    -0.06
    ambre
    -0.06
    CodeAt
    -0.06
    itchens
    -0.06
    lei
    -0.06
    POSITIVE LOGITS
    ož
    0.07
    _INST
    0.07
    ìĬ´
    0.07
    .gamma
    0.07
    uggle
    0.06
    _least
    0.06
    ÏĥÏĥα
    0.06
    ugg
    0.06
     Ñģоп
    0.06
     listing
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.