© 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 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. 29584
    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
     Bangalore
    -0.07
     Mohammed
    -0.07
     needing
    -0.06
     Chennai
    -0.06
    ket
    -0.06
     Tamil
    -0.06
    558
    -0.06
    iek
    -0.06
     fluids
    -0.06
    H
    -0.05
    POSITIVE LOGITS
    ftime
    0.08
     chaud
    0.08
    letal
    0.08
    JWT
    0.07
    ãĥ¼ãĥIJ
    0.07
     faz
    0.07
    atto
    0.07
     McCart
    0.07
     Mehr
    0.07
    ichert
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.