© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80310
    Prev
    Next
    INDEX
    Explanations

    references to product displays and upcoming events

    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
     Gaw
    -0.06
    iel
    -0.06
    ancell
    -0.06
    -figure
    -0.06
    xn
    -0.06
    à¹Īà¸Ńà¸Ļ
    -0.06
    ettes
    -0.06
     figure
    -0.05
    .Internal
    -0.05
    idel
    -0.05
    POSITIVE LOGITS
     booth
    0.09
     delegation
    0.08
     demonstrations
    0.08
     demonstration
    0.08
    Ģ
    0.08
     ÑģÑĤен
    0.07
    eyin
    0.07
    -demo
    0.07
     Demonstr
    0.07
    оÑĢаÑı
    0.07
    Activations Density 0.014%

    No Known Activations