© 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. 42620
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and their associated values

    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
    igt
    -0.07
     hood
    -0.06
    agit
    -0.06
    uly
    -0.06
    1
    -0.06
    ib
    -0.06
    éré
    -0.06
    ag
    -0.06
    nic
    -0.06
     sho
    -0.06
    POSITIVE LOGITS
    argout
    0.08
    Prostit
    0.07
    awi
    0.07
    ÄĽÅ¾
    0.07
    OrDefault
    0.07
    aternion
    0.07
    iao
    0.07
    Ñĩим
    0.07
    -toggler
    0.07
    ãģĿãģĨãģª
    0.06
    Activations Density 0.003%

    No Known Activations