© 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. 116615
    Prev
    Next
    INDEX
    Explanations

    prefixes related to historical time periods or themes

    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
    ãĥĭãĥ¼
    -0.09
    gow
    -0.07
    Ñĩи
    -0.07
     klu
    -0.07
    elm
    -0.07
    åħ·
    -0.06
    chin
    -0.06
     klin
    -0.06
    åĽ½äº§
    -0.06
     Fut
    -0.06
    POSITIVE LOGITS
    yte
    0.07
    /post
    0.07
    ubby
    0.07
    ouse
    0.06
    381
    0.06
    uer
    0.06
    ĸī
    0.06
    arih
    0.06
    Pub
    0.06
     existing
    0.06
    Activations Density 0.007%

    No Known Activations