© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84538
    Prev
    Next
    INDEX
    Explanations

    terms related to impairment or intoxication in the context of driving incidents

    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
    emark
    -0.06
    ialog
    -0.06
    coli
    -0.06
    embers
    -0.06
    eson
    -0.06
    agara
    -0.06
    118
    -0.05
     esc
    -0.05
     Arm
    -0.05
    atalog
    -0.05
    POSITIVE LOGITS
     impairment
    0.08
    orman
    0.07
     drug
    0.07
    ambre
    0.07
     impaired
    0.07
    interop
    0.07
     dangerous
    0.07
    imson
    0.06
     crash
    0.06
    caff
    0.06
    Activations Density 0.002%

    No Known Activations