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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 129219
    Prev
    Next
    INDEX
    Explanations

    btn

    np_max-act · gemini-2.0-flash

    HTML form elements and their attributes.

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

    The neuron flags occurrences of the Bootstrap “btn” class on button elements.

    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
    kara
    -0.08
     فرهنگی
    -0.06
    cliffe
    -0.06
    !=
    -0.06
    сон
    -0.06
     IB
    -0.06
     emple
    -0.06
    igion
    -0.06
    Resume
    -0.06
     email
    -0.06
    POSITIVE LOGITS
    []>(
    0.07
    .readInt
    0.07
     vibe
    0.07
     falta
    0.06
     Ramsey
    0.06
    /response
    0.06
     Leg
    0.06
     Vol
    0.06
     بلغ
    0.06
    -In
    0.06
    Activations Density 0.001%

    No Known Activations