© 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. 105459
    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
     study
    -0.06
     labeled
    -0.06
     pg
    -0.06
    ansa
    -0.06
     endeavor
    -0.06
     Weg
    -0.06
    alom
    -0.06
     favorable
    -0.06
     favor
    -0.05
     honored
    -0.05
    POSITIVE LOGITS
    iefs
    0.07
    ude
    0.07
    åłĤ
    0.07
     schle
    0.07
    uble
    0.07
    utive
    0.07
    engeance
    0.07
    iffin
    0.07
    uft
    0.07
    еди
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.