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. 84790
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on identifiers of form‐validation rules and field names (e.g. “firstname,” “email,” “password,” etc.) in jQuery Validate configurations.

    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
     gigantic
    -0.07
     templates
    -0.07
    _ts
    -0.06
     bombed
    -0.06
    usal
    -0.06
    CNN
    -0.06
    visualization
    -0.06
     Consolid
    -0.06
     idols
    -0.06
    玛
    -0.06
    POSITIVE LOGITS
     uploads
    0.07
    ',{↵
    0.07
     Sexe
    0.07
    amble
    0.07
    ?'
    0.06
    ระด
    0.06
     Ад
    0.06
     {[%
    0.06
    &amp
    0.06
     els
    0.06
    Activations Density 0.015%

    No Known Activations