© 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. 68909
    Prev
    Next
    INDEX
    Explanations

    Technical terminology

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on two-word noun-noun or noun-noun-like compound phrases.

    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
    Av
    -0.06
     llev
    -0.06
     운영
    -0.06
     kennen
    -0.06
     Hydro
    -0.06
    tex
    -0.06
     Algorithms
    -0.06
    	SET
    -0.06
     журн
    -0.06
     klíč
    -0.06
    POSITIVE LOGITS
     oath
    0.07
     月
    0.06
    امه
    0.06
    (instr
    0.06
     TLabel
    0.06
    :white
    0.06
     pra
    0.06
    .getById
    0.06
    ','=',$
    0.06
    體
    0.06
    Activations Density 0.128%

    No Known Activations