© 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. 15-LLAMASCOPE-RES-131K
    11. 86339
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain dates or numerical information

    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
    Å¡en
    -0.07
     opak
    -0.07
     invariant
    -0.07
    emap
    -0.06
    Ñĥб
    -0.06
    ç¿
    -0.06
    ován
    -0.06
    icl
    -0.06
     merk
    -0.06
    à¥įà¤Łà¤°
    -0.06
    POSITIVE LOGITS
    AutoSize
    0.07
    erp
    0.06
    ppo
    0.06
     Revenge
    0.06
    ycop
    0.06
    izontally
    0.06
    uye
    0.06
    pios
    0.06
    utos
    0.06
     convenience
    0.06
    Activations Density 0.001%

    No Known Activations