© 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. 86195
    Prev
    Next
    INDEX
    Explanations

    references to vehicle mileage and odometer readings

    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
     IDS
    -0.07
    asics
    -0.07
    ategories
    -0.07
    emento
    -0.07
    /lists
    -0.07
     ISI
    -0.07
     Seznam
    -0.06
    utom
    -0.06
    è³ŀ
    -0.06
    ektir
    -0.06
    POSITIVE LOGITS
     odom
    0.06
     spa
    0.06
     condition
    0.06
     mileage
    0.06
     since
    0.06
     corner
    0.06
    ycop
    0.06
    edis
    0.06
    _since
    0.06
    urm
    0.06
    Activations Density 0.003%

    No Known Activations