© 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. 116454
    Prev
    Next
    INDEX
    Explanations

    modal verbs paired with forms of the verb "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
    kur
    -0.07
    cid
    -0.07
    _DOM
    -0.07
    .nlm
    -0.07
    oreach
    -0.07
    deniz
    -0.07
    jak
    -0.06
    iy
    -0.06
     opráv
    -0.06
    è£ľ
    -0.06
    POSITIVE LOGITS
     used
    0.09
    used
    0.09
     use
    0.09
    -used
    0.07
    use
    0.07
    Ñĥж
    0.07
     Used
    0.07
    Used
    0.07
    .use
    0.07
    trx
    0.07
    Activations Density 0.027%

    No Known Activations