© 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. 27925
    Prev
    Next
    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot explicitly erotic sexual content—graphic references to sexual acts and anatomy.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    narratives involving playful or humorous scenarios with characters experiencing light-hearted, physical interactions.

    oai_token-act-pair · gpt-4o-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
    	e
    -0.07
    (Form
    -0.06
    (load
    -0.06
    .sp
    -0.06
    (IO
    -0.06
    .:
    -0.06
    (mx
    -0.06
    (gr
    -0.06
     Quad
    -0.06
    стория
    -0.06
    POSITIVE LOGITS
     coworkers
    0.07
     cowork
    0.07
     decor
    0.06
    _NEAREST
    0.06
     полу
    0.06
    UFACT
    0.06
     ADM
    0.06
     gri
    0.06
     textual
    0.06
     치
    0.06
    Activations Density 0.057%

    No Known Activations