© 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. 5972
    Prev
    Next
    INDEX
    Explanations

    -right

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens—especially CSS measurement values (e.g. “25”, “px”, “2.537…”)—highlighting any numbers in style declarations.

    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
    Bean
    -0.07
     مناسب
    -0.06
    _probs
    -0.06
    ्पन
    -0.06
    _rb
    -0.06
     Required
    -0.06
    .easing
    -0.06
     Austria
    -0.06
    .posts
    -0.06
    /String
    -0.06
    POSITIVE LOGITS
     činnost
    0.07
    	yield
    0.07
     vä
    0.07
    	Item
    0.06
     franchises
    0.06
     inne
    0.06
     techn
    0.06
    уються
    0.06
     oxide
    0.06
    Priv
    0.06
    Activations Density 0.003%

    No Known Activations