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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 40473
    Prev
    Next
    INDEX
    Explanations

    HTML elements

    np_max-act · gemini-2.0-flash

    HTML and CSS structure related to Bootstrap components.

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

    The neuron fires on Bootstrap “card” component class names (e.g. card-body, card-title, card-text, card-header, card-img-top).

    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
    NT
    -0.06
    ival
    -0.06
    Lets
    -0.06
    Iran
    -0.06
     Lens
    -0.06
    .sem
    -0.06
     trackers
    -0.06
    NETWORK
    -0.06
    /boot
    -0.06
     promoted
    -0.06
    POSITIVE LOGITS
    iants
    0.07
    ثير
    0.07
     percentage
    0.06
    areth
    0.06
    нию
    0.06
    -leading
    0.06
    鳥
    0.06
     admiration
    0.06
    zie
    0.06
    Deprecated
    0.06
    Activations Density 0.005%

    No Known Activations