© 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. 15-RESID-POST-AA
    11. 45175
    Prev
    Next
    INDEX
    Explanations

    hiding

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mir
    -0.07
    →
    -0.07
    ta
    -0.06
     Shan
    -0.06
     legalize
    -0.06
    面積
    -0.06
     slamming
    -0.06
    �
    -0.06
     vil
    -0.06
    .setTextSize
    -0.06
    POSITIVE LOGITS
     aggregates
    0.06
     фундамент
    0.06
    (robot
    0.06
     Alloy
    0.06
    drivers
    0.06
     легко
    0.06
    cycles
    0.06
    umbles
    0.06
     Plaint
    0.06
     darm
    0.06
    Activations Density 0.010%

    No Known Activations