© 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. 31423
    Prev
    Next
    INDEX
    Explanations

    expressions of recognition and accolades

    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
    ãĤªãĥª
    -0.08
    noch
    -0.08
     UNU
    -0.07
    emetery
    -0.07
    ạp
    -0.07
    аÑĢÑı
    -0.07
    ampus
    -0.07
     мил
    -0.07
    asel
    -0.07
    boro
    -0.07
    POSITIVE LOGITS
     sir
    0.06
    esson
    0.06
     Ker
    0.06
     AF
    0.06
     rein
    0.06
     Sly
    0.06
    uat
    0.05
    swick
    0.05
     Bern
    0.05
     Soda
    0.05
    Activations Density 0.000%

    No Known Activations