© 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. 94606
    Prev
    Next
    INDEX
    Explanations

    prompts for user input in a form

    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
    ntag
    -0.07
    atab
    -0.07
     Jak
    -0.07
    æĮ¯ãĤĬ
    -0.07
    ATAB
    -0.07
    PostExecute
    -0.06
    enal
    -0.06
    CurrentValue
    -0.06
    ngo
    -0.06
    uxt
    -0.06
    POSITIVE LOGITS
    inh
    0.07
     عز
    0.06
    tron
    0.06
    cro
    0.06
    SEA
    0.06
     quyá»ģn
    0.06
    ung
    0.06
    ocale
    0.06
     your
    0.05
    âħ
    0.05
    Activations Density 0.008%

    No Known Activations