© 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. 55524
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    HTML and CSS elements related to form structures and their properties.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects HTML elements that include or reference external resources (e.g. link/script tags or any tag with href, src, data-url, etc.).

    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
    建
    -0.07
     ES
    -0.07
    Demon
    -0.07
    _De
    -0.07
    adil
    -0.07
     millennium
    -0.06
     schemes
    -0.06
     издел
    -0.06
     Kemp
    -0.06
     coined
    -0.06
    POSITIVE LOGITS
    .active
    0.06
     مرحله
    0.06
    .damage
    0.06
    ificent
    0.06
    tring
    0.06
    .movie
    0.06
     Vanity
    0.06
    setEnabled
    0.06
     thuis
    0.06
     Heading
    0.06
    Activations Density 0.005%

    No Known Activations