© 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. 79830
    Prev
    Next
    INDEX
    Explanations

    citations or mentions of authors and publication dates

    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
    ify
    -0.07
    ohan
    -0.07
    agh
    -0.06
    urt
    -0.06
    riot
    -0.06
    rey
    -0.06
    functional
    -0.06
     Reconstruction
    -0.06
    (dot
    -0.06
    toBeDefined
    -0.06
    POSITIVE LOGITS
    òng
    0.07
    urette
    0.06
    ocu
    0.06
    .prepend
    0.06
     tasar
    0.06
    ndx
    0.06
     Maz
    0.06
    inston
    0.06
    sage
    0.06
    ắp
    0.06
    Activations Density 0.001%

    No Known Activations