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. 126837
    Prev
    Next
    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of Django form handling—especially occurrences of the variable “form” and its methods like is_valid() and save().

    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
     Бі
    -0.07
    Dic
    -0.06
    comma
    -0.06
    359
    -0.06
    css
    -0.06
    .MODEL
    -0.06
    ';';
    -0.06
     tôn
    -0.06
     NV
    -0.06
     sass
    -0.06
    POSITIVE LOGITS
     accountant
    0.07
    >>&
    0.07
    getWindow
    0.06
     sobie
    0.06
     Compound
    0.06
    means
    0.06
    [u
    0.06
     Exercises
    0.06
     csvfile
    0.06
    .green
    0.06
    Activations Density 0.005%

    No Known Activations