© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38615
    Prev
    Next
    INDEX
    Explanations

    sitting/on

    np_max-act · gemini-2.0-flash

    content related to erotic themes and adult situations.

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

    This neuron detects words or word fragments indicating the act or position of sitting.

    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
     ecs
    -0.07
     田
    -0.07
    .hostname
    -0.07
     specifying
    -0.07
     bb
    -0.06
     Copy
    -0.06
     Stub
    -0.06
     recursos
    -0.06
    _clean
    -0.06
    Cleaning
    -0.06
    POSITIVE LOGITS
    mt
    0.06
    선거
    0.06
    μμε
    0.06
    PG
    0.06
     divert
    0.06
     बय
    0.06
    dependence
    0.06
    .getLogin
    0.06
     неиз
    0.06
     jmen
    0.06
    Activations Density 0.016%

    No Known Activations