© 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. 108662
    Prev
    Next
    INDEX
    Explanations

    references to actions involving events and their modifications

    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
    icari
    -0.08
    avou
    -0.07
    ingleton
    -0.07
    erval
    -0.07
    ÄĽn
    -0.07
    eum
    -0.07
    unsch
    -0.07
    _REUSE
    -0.07
    ãģĻãĤĭãģ¨
    -0.06
     uveden
    -0.06
    POSITIVE LOGITS
     yesterday
    0.15
     earlier
    0.14
     Yesterday
    0.12
     recently
    0.11
    Yesterday
    0.10
     originally
    0.10
     previously
    0.10
     previous
    0.10
     recent
    0.10
     last
    0.10
    Activations Density 0.050%

    No Known Activations