© 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. 31038
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    adol
    -0.07
    DITION
    -0.07
    ebi
    -0.07
    ylon
    -0.07
    ishi
    -0.07
    UCT
    -0.07
    HeaderCode
    -0.07
    λÎŃον
    -0.07
    ýn
    -0.07
    BOOLE
    -0.07
    POSITIVE LOGITS
    !
    0.06
     ÄĮer
    0.06
    اا
    0.06
    ابر
    0.06
    355
    0.06
    mith
    0.06
     foc
    0.06
    διά
    0.06
     Clerk
    0.06
    нав
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.