© 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. 53716
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "was" related to notable achievements or identities

    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
    imitive
    -0.07
    -counter
    -0.06
     наÑħод
    -0.06
    ilon
    -0.06
    arez
    -0.06
    ipping
    -0.06
    eden
    -0.06
    onders
    -0.06
    ingleton
    -0.06
    ideographic
    -0.06
    POSITIVE LOGITS
     born
    0.08
     Born
    0.07
     instrumental
    0.07
     rot
    0.07
     refresh
    0.07
     himself
    0.07
    289
    0.06
    çĶŁ
    0.06
     insist
    0.06
     contemporary
    0.06
    Activations Density 0.027%

    No Known Activations