© 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. 15-LLAMASCOPE-RES-131K
    11. 86505
    Prev
    Next
    INDEX
    Explanations

    references to tires and tire-related terminology

    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
    inar
    -0.07
    ness
    -0.07
    roe
    -0.07
    ropol
    -0.06
     else
    -0.06
    rium
    -0.06
    ary
    -0.06
    obe
    -0.06
    ivity
    -0.06
     Rick
    -0.06
    POSITIVE LOGITS
    óz
    0.09
    edback
    0.07
    gio
    0.07
    ध
    0.07
    /cards
    0.07
    å¿ł
    0.07
    ấc
    0.07
    anj
    0.07
    ugas
    0.06
    ÌĢ
    0.06
    Activations Density 0.004%

    No Known Activations