© 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. 95933
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was"

    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
    .patch
    -0.07
    rá
    -0.06
    ewater
    -0.06
    иной
    -0.06
     McCorm
    -0.06
     Morph
    -0.06
    ire
    -0.06
    ioneer
    -0.06
    irim
    -0.06
    _callable
    -0.06
    POSITIVE LOGITS
     born
    0.09
     childhood
    0.08
     Born
    0.08
    Born
    0.07
     recently
    0.07
    born
    0.07
    ä¾Ľ
    0.06
     himself
    0.06
    ear
    0.06
    abei
    0.06
    Activations Density 0.025%

    No Known Activations