Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91861
    Prev
    Next
    INDEX
    Explanations

    programming questions and answers

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of selection‐event handling (e.g. “react to a selection event,” “SELECTED event,” and related event‐listener code).

    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
     Jennifer
    -0.07
    ills
    -0.07
    asses
    -0.06
    	RTLI
    -0.06
    .findall
    -0.06
    ILLS
    -0.06
    	mask
    -0.06
    فاع
    -0.06
     Blessed
    -0.06
    .react
    -0.06
    POSITIVE LOGITS
     (?)
    0.07
    nutí
    0.07
     wifi
    0.07
    roadcast
    0.06
    catch
    0.06
     цю
    0.06
    вердж
    0.06
     knocking
    0.06
     dcc
    0.06
    arts
    0.06
    Activations Density 0.032%

    No Known Activations