© 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. 9-LLAMASCOPE-RES-131K
    11. 99227
    Prev
    Next
    INDEX
    Explanations

    specific times mentioned in the context of events

    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
     Myers
    -0.07
    ruba
    -0.07
    uling
    -0.07
    ilip
    -0.06
    ellas
    -0.06
    -fontawesome
    -0.06
    uncios
    -0.06
    .raises
    -0.06
    spor
    -0.06
    createForm
    -0.06
    POSITIVE LOGITS
    uns
    0.07
     Bart
    0.06
    emie
    0.06
    aju
    0.06
     jig
    0.06
    egra
    0.06
    ìķħ
    0.06
    rig
    0.06
     ÅĻÃŃj
    0.06
    oji
    0.06
    Activations Density 0.006%

    No Known Activations