© 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. 57058
    Prev
    Next
    INDEX
    Explanations

    various historical events

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on explicit mentions of the word “clitoris,” especially in graphic sexual 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
     сах
    -0.07
     сух
    -0.07
     졸
    -0.07
     dictate
    -0.07
     řada
    -0.07
    เมตร
    -0.06
    RSpec
    -0.06
    ヒ
    -0.06
    ِه
    -0.06
    ีโ
    -0.06
    POSITIVE LOGITS
    GRADE
    0.06
    資料
    0.06
    .interval
    0.06
     Enhancement
    0.05
    _Status
    0.05
    (""
    0.05
    etroit
    0.05
    .Graph
    0.05
     Deprecated
    0.05
    lices
    0.05
    Activations Density 13.939%

    No Known Activations