© 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. 116335
    Prev
    Next
    INDEX
    Explanations

    user interface elements and actions related to e-commerce and web forms

    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
    ango
    -0.07
    AndGet
    -0.07
    اÙĨس
    -0.07
    ãĤıãģij
    -0.06
     {}:
    -0.06
    eson
    -0.06
    eken
    -0.06
     differently
    -0.06
    ournals
    -0.06
    illi
    -0.06
    POSITIVE LOGITS
    (er
    0.07
    </
    0.07
    ór
    0.07
    vant
    0.06
    _exempt
    0.06
    stüt
    0.06
     disadv
    0.06
    idlo
    0.06
    mma
    0.06
    vell
    0.06
    Activations Density 0.026%

    No Known Activations