© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    instances of the word "scar" or its variations

    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
    yar
    -0.08
    -ÑĤо
    -0.07
    tempt
    -0.07
    stile
    -0.07
    iasm
    -0.07
    gaard
    -0.07
    kr
    -0.07
    .Automation
    -0.07
    ouro
    -0.07
    onis
    -0.07
    POSITIVE LOGITS
    oÄį
    0.08
    anton
    0.08
    ieri
    0.08
    let
    0.07
    borough
    0.07
     Cheng
    0.06
    lett
    0.06
    ified
    0.06
    raf
    0.06
    DAQ
    0.06
    Activations Density 0.005%

    No Known Activations