© 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. 102904
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    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
     overlap
    -0.07
    _DIP
    -0.06
    responses
    -0.06
    .visualization
    -0.06
    ampler
    -0.06
    ANDOM
    -0.06
     marriages
    -0.06
     facing
    -0.06
    frag
    -0.06
     họa
    -0.06
    POSITIVE LOGITS
     ~(
    0.07
     alacak
    0.07
     Hawk
    0.06
    eyen
    0.06
    \",\"
    0.06
     amounted
    0.06
    ěst
    0.06
     kond
    0.06
     Бер
    0.06
    [col
    0.06
    Activations Density 0.003%

    No Known Activations