© 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. 57796
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

    np_max-act · gemini-2.0-flash

    The neuron does not activate for any tokens, i.e. it remains silent and does not detect any specific features.

    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
    _network
    -0.08
     Builds
    -0.08
     appealed
    -0.07
     pandas
    -0.07
    VIDIA
    -0.07
     engr
    -0.07
     knocking
    -0.07
    센
    -0.07
     builds
    -0.07
    _line
    -0.07
    POSITIVE LOGITS
    .Categories
    0.06
     tém
    0.06
     Vị
    0.06
     skimage
    0.06
     nejvyšší
    0.06
    .fromLTRB
    0.05
     Jest
    0.05
     {!
    0.05
     {

↵
    0.05
     '.'
    0.05
    Activations Density 0.012%

    No Known Activations