© 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. 104257
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ol" and actions involving rolling

    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
    омен
    -0.07
     pie
    -0.07
    pez
    -0.06
    èµ°
    -0.06
    asaki
    -0.06
     sav
    -0.06
     pizza
    -0.06
    γά
    -0.06
     pois
    -0.06
    isinden
    -0.06
    POSITIVE LOGITS
    .screen
    0.08
     Ebola
    0.08
     screened
    0.07
     screenings
    0.07
    -screen
    0.07
    icter
    0.07
    Canceled
    0.07
    SCREEN
    0.07
     screening
    0.07
     Health
    0.07
    Activations Density 0.000%

    No Known Activations