© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110399
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash

    The neuron fires on the CSS background‐image “url(…)” syntax—especially the “url” token and its following opening parenthesis.

    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
    责
    -0.06
     陳
    -0.06
    琴
    -0.06
    ensa
    -0.06
    _chg
    -0.06
    _PG
    -0.06
     embodies
    -0.06
    <Transform
    -0.06
    .Cursor
    -0.06
     shaded
    -0.06
    POSITIVE LOGITS
    _pose
    0.07
     Sections
    0.06
     ότι
    0.06
     долго
    0.06
     здесь
    0.06
    ポイント
    0.06
    	ad
    0.06
     lidí
    0.06
    :r
    0.06
     Only
    0.06
    Activations Density 0.023%

    No Known Activations