© 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. 2210
    Prev
    Next
    INDEX
    Explanations

    descriptions of artistic technique and craftsmanship

    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
     U
    -0.06
     existence
    -0.06
     outside
    -0.05
     events
    -0.05
     Useful
    -0.05
    اÙħÛĮÙĨ
    -0.05
     thwart
    -0.05
     reports
    -0.05
    antis
    -0.05
     sealed
    -0.05
    POSITIVE LOGITS
     technique
    0.09
    æĬĢ
    0.09
    .scalablytyped
    0.09
     skill
    0.09
    conde
    0.08
     mastery
    0.08
    -master
    0.08
     ìĨ
    0.08
     skills
    0.08
     subt
    0.07
    Activations Density 0.047%

    No Known Activations