© 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. 7094
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    references to chemical compounds and their structures in scientific literature.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the numeric measurement values (especially floating‐point numbers and units) in detailed scientific data sections, e.g. crystallographic parameters.

    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
    [
    -0.06
    six
    -0.06
    听到
    -0.06
     pazar
    -0.06
    instruction
    -0.06
     différentes
    -0.06
    اعت
    -0.06
    istung
    -0.06
    006
    -0.05
    loha
    -0.05
    POSITIVE LOGITS
    เทศ
    0.08
     일반
    0.08
     Planned
    0.07
    (CONFIG
    0.07
     ResultSet
    0.07
    uant
    0.07
    _Load
    0.07
    되고
    0.06
     SHOW
    0.06
    .onViewCreated
    0.06
    Activations Density 0.001%

    No Known Activations