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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39719
    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
    sans
    -0.07
    efs
    -0.06
    Fuck
    -0.06
     religious
    -0.06
     aka
    -0.06
     Vaults
    -0.06
     preached
    -0.06
     fucking
    -0.06
     fuck
    -0.06
    -c
    -0.06
    POSITIVE LOGITS
     ucwords
    0.07
    족
    0.07
     accred
    0.07
     Bun
    0.07
     Chick
    0.07
    .createFrom
    0.07
    ignon
    0.07
    rypted
    0.07
    ÑģÑĤÑĢа
    0.07
    imir
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.