© 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. 14374
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "both."

    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
    eer
    -0.06
    iro
    -0.06
     either
    -0.06
    ds
    -0.06
    afe
    -0.06
    ancellable
    -0.06
    ourg
    -0.06
    hiro
    -0.06
     Hiro
    -0.05
    pon
    -0.05
    POSITIVE LOGITS
    InParameter
    0.08
     sexes
    0.08
    azel
    0.08
    StrictEqual
    0.07
    ché
    0.07
    esiz
    0.07
    gaard
    0.07
    oomla
    0.07
    xDA
    0.07
    chers
    0.07
    Activations Density 0.009%

    No Known Activations