© 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. 129848
    Prev
    Next
    INDEX
    Explanations

    polyester

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on specific chemical compound or polymer names in the text.

    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
    Johnson
    -0.07
     Chim
    -0.07
     Han
    -0.06
     chicken
    -0.06
    Val
    -0.06
     harmful
    -0.06
    -co
    -0.06
    _TREE
    -0.06
    (surface
    -0.06
    Ин
    -0.06
    POSITIVE LOGITS
     polyester
    0.12
     Polyester
    0.10
    esper
    0.07
     prostituer
    0.07
    inese
    0.07
    elper
    0.06
    ester
    0.06
    	RTLI
    0.06
    orElse
    0.06
    шей
    0.06
    Activations Density 0.001%

    No Known Activations