© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92140
    Prev
    Next
    INDEX
    Explanations

    dangerous situations

    np_max-act · gemini-2.0-flash

    The neuron detects words that describe dangerous or hazardous conditions (e.g. “dangerous,” “unsafe,” “critical”)—especially in the context of roads or safety risks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DESIGN
    -0.07
    able
    -0.07
    ícul
    -0.07
     FC
    -0.07
    _th
    -0.06
    罗
    -0.06
    ABLE
    -0.06
     piping
    -0.06
     pep
    -0.06
     Iter
    -0.06
    POSITIVE LOGITS
     rushed
    0.07
    .link
    0.07
    	delete
    0.07
     cứu
    0.07
    .dateTimePicker
    0.06
    "}>↵
    0.06
    Trivia
    0.06
     Foley
    0.06
     gece
    0.06
     контр
    0.06
    Activations Density 0.019%

    No Known Activations