© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89003
    Prev
    Next
    INDEX
    Explanations

    Medical transport/death

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of injured or ill people being moved—e.g. “transported,” “taken,” etc.—to medical care.

    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
    	RETURN
    -0.07
     อำ
    -0.07
     language
    -0.07
    тя
    -0.07
    -channel
    -0.06
     prend
    -0.06
    usal
    -0.06
    Makes
    -0.06
     waist
    -0.06
     technolog
    -0.06
    POSITIVE LOGITS
     '[
    0.06
    اوي
    0.06
     fotos
    0.06
    aos
    0.06
     politically
    0.06
     шляхом
    0.06
     Florida
    0.06
    .zero
    0.06
     místa
    0.06
     tweaked
    0.06
    Activations Density 0.016%

    No Known Activations