© 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. 108835
    Prev
    Next
    INDEX
    Explanations

    image

    np_max-act · gemini-2.0-flash

    themes related to body image and the impact of societal standards on self-perception.

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

    The neuron activates on terms related to bodily appearance and image (e.g. body, image, beauty, physical change), i.e. it detects mentions of body‐image concerns and physical changes.

    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
    (lo
    -0.06
    ате
    -0.06
    nten
    -0.06
    Detect
    -0.06
     VIDEO
    -0.06
    복지
    -0.06
     Ach
    -0.05
     Quickly
    -0.05
    _TA
    -0.05
    lá
    -0.05
    POSITIVE LOGITS
    _;
    0.07
     blitz
    0.07
     Tribunal
    0.07
     DropDownList
    0.07
    Alive
    0.07
    jumbotron
    0.06
    ứt
    0.06
    -tab
    0.06
    320
    0.06
    ф
    0.06
    Activations Density 0.018%

    No Known Activations