© 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. 9369
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    references to abortion and reproductive rights discussions.

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

    The neuron fires on evaluative reaction language in news‐style text—especially verbs and phrases expressing approval or praise (e.g. “welcomed,” “applauded,” “reacts,” “says”).

    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
    Failure
    -0.07
     テ
    -0.07
    Mal
    -0.07
     Mack
    -0.06
     culinary
    -0.06
     الص
    -0.06
     Mustafa
    -0.06
     Up
    -0.06
     sorted
    -0.06
    Def
    -0.06
    POSITIVE LOGITS
    اج
    0.07
     �
    0.06
    .prepareStatement
    0.06
    .Filters
    0.06
     Abstract
    0.06
    /${
    0.06
     ultr
    0.06
    ंग
    0.06
     "','
    0.06
    (fe
    0.06
    Activations Density 0.026%

    No Known Activations