© 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 EvalsExportsinterp-engineNEWAPI 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. 58072
    Prev
    Next
    INDEX
    Explanations

    Knitting/sewing blogs

    np_max-act · gemini-2.0-flash

    The neuron primarily detects mentions of hands-on craft activities and related project terms—words like “knitting,” “sewing,” “crochet,” “make,” “project,” etc.

    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
     unm
    -0.06
    От
    -0.06
    夫人
    -0.06
     нав
    -0.06
    uet
    -0.06
     han
    -0.06
    _ACT
    -0.06
     fout
    -0.06
    Coll
    -0.06
    alone
    -0.06
    POSITIVE LOGITS
     uphe
    0.08
     Dorothy
    0.07
     заліз
    0.07
     Phys
    0.07
     formerly
    0.06
    Shapes
    0.06
    define
    0.06
     srpna
    0.06
    ampa
    0.06
     tensorflow
    0.06
    Activations Density 0.020%

    No Known Activations