© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7380
    Prev
    Next
    INDEX
    Explanations

    .js

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of JavaScript `<script>` tags (i.e. “.js” script‐include statements).

    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
    victim
    -0.06
     Niagara
    -0.06
    {}".
    -0.06
     стен
    -0.06
    خذ
    -0.06
    	let
    -0.06
    OLEAN
    -0.06
    ่าน
    -0.06
    تباط
    -0.06
    getEmail
    -0.06
    POSITIVE LOGITS
    ائد
    0.07
     erle
    0.06
    ฬ
    0.06
     pulp
    0.06
    xea
    0.06
    erek
    0.06
    靈
    0.06
    irected
    0.06
    资源
    0.06
    养
    0.06
    Activations Density 0.002%

    No Known Activations