© 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 EvalsExportsAPI 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. 16349
    Prev
    Next
    INDEX
    Explanations

    references to appliance repair, specifically focusing on clothes dryers

    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
    assel
    -0.06
     Dil
    -0.06
    .tool
    -0.06
    ostel
    -0.06
    živ
    -0.06
     Millet
    -0.06
     binder
    -0.06
    dana
    -0.06
     Lamp
    -0.06
    elmet
    -0.06
    POSITIVE LOGITS
     è¶
    0.07
     sud
    0.06
    oins
    0.06
    afc
    0.06
     deter
    0.06
     Sud
    0.06
    idar
    0.06
    .codes
    0.06
    arios
    0.06
     finish
    0.06
    Activations Density 0.008%

    No Known Activations