© 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. 105351
    Prev
    Next
    INDEX
    Explanations

    references to specific types of documents or records

    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
    imes
    -0.08
    imson
    -0.08
    folio
    -0.08
    ollipop
    -0.08
    ovaly
    -0.07
    olly
    -0.07
    usk
    -0.07
    offee
    -0.07
    uzzer
    -0.07
    té
    -0.07
    POSITIVE LOGITS
    itz
    0.07
    ynet
    0.06
    avel
    0.06
     sund
    0.06
    urnal
    0.06
    -hour
    0.06
    ãĤ¤ãĤ¯
    0.06
    _dump
    0.06
    -clear
    0.06
    ously
    0.06
    Activations Density 0.033%

    No Known Activations