© 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. 91273
    Prev
    Next
    INDEX
    Explanations

    object

    np_max-act · gemini-2.0-flash

    The neuron activates on key computer‐vision task terms (e.g. object, recognition, segmentation, tracking).

    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
     Defaults
    -0.07
     flats
    -0.06
    IA
    -0.06
     arrogant
    -0.06
    mousedown
    -0.06
    Loader
    -0.06
    photos
    -0.06
    Sold
    -0.06
     wurde
    -0.06
    ';';
    -0.06
    POSITIVE LOGITS
     фун
    0.07
     سلس
    0.07
     Continental
    0.07
     Rob
    0.07
     SIN
    0.06
    ifestyles
    0.06
    ьте
    0.06
    :!
    0.06
    .Di
    0.06
    _med
    0.06
    Activations Density 0.015%

    No Known Activations