© 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. 38583
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special symbols within the text

    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
    tractor
    -0.07
     ÑĢÑı
    -0.07
    наÑħ
    -0.07
    phis
    -0.07
    YC
    -0.07
    Ä°ng
    -0.06
    asso
    -0.06
    _hor
    -0.06
    ascus
    -0.06
    tracts
    -0.06
    POSITIVE LOGITS
     Wick
    0.06
    istrovstvÃŃ
    0.06
    utex
    0.06
    itage
    0.06
     COVID
    0.05
    createElement
    0.05
    orian
    0.05
    arine
    0.05
    gener
    0.05
     Lands
    0.05
    Activations Density 0.000%

    No Known Activations