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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84494
    Prev
    Next
    INDEX
    Explanations

    cookie consent

    np_max-act · gemini-2.0-flash

    The neuron detects cookie‐consent notices, specifically mentions of “use of cookies” and agreement to cookie usage.

    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
    shit
    -0.07
     corres
    -0.07
     окт
    -0.06
    minute
    -0.06
    ifié
    -0.06
     triplet
    -0.06
     Expr
    -0.06
    _At
    -0.06
    िष
    -0.06
     circuits
    -0.06
    POSITIVE LOGITS
     accredited
    0.07
     Tactical
    0.07
    phalt
    0.07
     recruiting
    0.06
     autour
    0.06
     evaluated
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
     wasn
    0.06
     SCE
    0.06
    Time
    0.06
    Activations Density 0.002%

    No Known Activations