© 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. 57332
    Prev
    Next
    INDEX
    Explanations

    references to vehicle registration and identification

    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
    æĸŃ
    -0.07
     sortie
    -0.07
    tright
    -0.07
     Maison
    -0.07
    modx
    -0.07
     podp
    -0.07
    mgr
    -0.06
    æĸ·
    -0.06
    /Gate
    -0.06
     maison
    -0.06
    POSITIVE LOGITS
     plate
    0.09
     plates
    0.09
     car
    0.08
    Plate
    0.08
     Plate
    0.08
     state
    0.07
     Grill
    0.07
     State
    0.07
     Hem
    0.07
    .state
    0.06
    Activations Density 0.004%

    No Known Activations