© 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. 108050
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS link tags in a document

    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
    ---</
    -0.10
    Ø«ÛĮر
    -0.07
    _firestore
    -0.07
    ----</
    -0.07
    á»ĭch
    -0.07
    lama
    -0.07
    JSGlobal
    -0.07
    ायत
    -0.07
    achuset
    -0.07
    odesk
    -0.07
    POSITIVE LOGITS
     Morris
    0.07
     http
    0.06
     local
    0.06
     Hundred
    0.06
    http
    0.06
    624
    0.06
    .css
    0.06
    374
    0.06
     Hutchinson
    0.06
    åįİ
    0.06
    Activations Density 0.010%

    No Known Activations