© 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. 103867
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    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
     typically
    -0.06
     Kop
    -0.06
     must
    -0.06
    è«ĭ
    -0.06
    å¸ĮæľĽ
    -0.05
    ILD
    -0.05
    ór
    -0.05
     certainly
    -0.05
     Lantern
    -0.05
    plr
    -0.05
    POSITIVE LOGITS
     properly
    0.09
     olab
    0.09
    proper
    0.08
     proper
    0.07
     Proper
    0.07
    ftar
    0.07
    aping
    0.07
    neys
    0.07
    olleyError
    0.07
    Scrollbar
    0.07
    Activations Density 0.020%

    No Known Activations