© 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. 41117
    Prev
    Next
    INDEX
    Explanations

    Services/product descriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on standalone, title‐style phrases (e.g. section or feature headings) in product or listing text.

    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
     Dragon
    -0.07
    ůsob
    -0.07
    .addValue
    -0.06
     slapped
    -0.06
    Formats
    -0.06
    istinguished
    -0.06
     dominant
    -0.06
    Degree
    -0.06
    OrElse
    -0.06
     Mechanics
    -0.06
    POSITIVE LOGITS
    омет
    0.06
    !=(
    0.06
    wil
    0.06
     che
    0.06
     gamb
    0.06
     pres
    0.06
    แท
    0.06
     <-
    0.06
     leftover
    0.06
     وارد
    0.06
    Activations Density 0.023%

    No Known Activations