© 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. 14185
    Prev
    Next
    INDEX
    Explanations

    verbs associated with beginnings and transitions

    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
    bia
    -0.07
    /math
    -0.06
     infinit
    -0.06
    ÙĪج
    -0.06
    odge
    -0.06
    Controls
    -0.06
    вин
    -0.06
    ÄĽn
    -0.06
    ptom
    -0.06
    agh
    -0.06
    POSITIVE LOGITS
    OffsetTable
    0.08
    ayed
    0.08
    enville
    0.08
    edException
    0.07
    alsa
    0.07
    Portal
    0.07
    elpers
    0.07
    ayd
    0.07
    cket
    0.07
    fir
    0.07
    Activations Density 0.036%

    No Known Activations