© 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. 9-LLAMASCOPE-RES-131K
    11. 97912
    Prev
    Next
    INDEX
    Explanations

    references to locations in West Virginia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     squ
    -0.07
     out
    -0.06
    âĢ¦↵
    -0.05
    fol
    -0.05
    766
    -0.05
     release
    -0.05
     dumb
    -0.05
     partial
    -0.05
    ado
    -0.05
    dera
    -0.05
    POSITIVE LOGITS
    áºł
    0.09
     -*-č↵
    0.08
    isel
    0.08
    .osgi
    0.08
    /WebAPI
    0.08
    NM
    0.07
    xcb
    0.07
    teki
    0.07
    .XR
    0.07
    éĨ´
    0.07
    Activations Density 0.008%

    No Known Activations