© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91207
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    statements related to education, specifically measures and policies affecting the arts and creative subjects in schools.

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

    This neuron flags language that describes legal or policy conflicts and enforcement actions in political contexts.

    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
     typing
    -0.08
    	name
    -0.07
     timings
    -0.06
     spinning
    -0.06
     clustering
    -0.06
     environments
    -0.06
     climb
    -0.06
     Spend
    -0.06
     Dysfunction
    -0.06
    cludes
    -0.06
    POSITIVE LOGITS
    enstein
    0.07
    $input
    0.06
     реж
    0.06
    ハイ
    0.06
    pillar
    0.06
    mis
    0.06
    令
    0.06
    ัตร
    0.06
    ่สามารถ
    0.06
     перет
    0.06
    Activations Density 0.031%

    No Known Activations