© 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. 93192
    Prev
    Next
    INDEX
    Explanations

    information related to traffic accidents and emergency responses

    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
    ERY
    -0.07
    ych
    -0.06
     Kling
    -0.06
    ssf
    -0.06
    .sponge
    -0.06
     inaug
    -0.06
     Mort
    -0.06
     пÑĢоÑĪ
    -0.06
    æĶ¶å½ķ
    -0.06
     Cly
    -0.06
    POSITIVE LOGITS
     conscious
    0.07
    rollo
    0.07
    -pin
    0.07
    -conscious
    0.06
    ushi
    0.06
     unconscious
    0.06
     Discount
    0.06
    landa
    0.06
     consciousness
    0.06
     اÙĦÙĬ
    0.06
    Activations Density 0.014%

    No Known Activations