© 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. 2396
    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
     ours
    -0.07
    Ìĥ
    -0.07
    âĢª
    -0.07
    обов
    -0.07
    mdl
    -0.07
    ï¿
    -0.06
    (çģ«
    -0.06
    ###############################################################################↵
    -0.06
     Affero
    -0.06
    že
    -0.06
    POSITIVE LOGITS
     thang
    0.06
    lord
    0.06
     Spar
    0.06
    .opend
    0.06
     ar
    0.06
     laid
    0.06
     citizen
    0.06
    55
    0.06
    allee
    0.05
     sp
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.