© 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. 19-RESID-POST-AA
    11. 109747
    Prev
    Next
    INDEX
    Explanations

    6

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (cuda
    -0.06
     Yas
    -0.06
    Cy
    -0.06
    缘
    -0.06
     KAR
    -0.06
     Oz
    -0.06
     Ori
    -0.06
     vur
    -0.06
     Ced
    -0.06
     Cand
    -0.05
    POSITIVE LOGITS
     Intent
    0.07
    hc
    0.07
    нолог
    0.07
    ’acc
    0.07
    	category
    0.07
     alarm
    0.06
    .self
    0.06
    ίδα
    0.06
    _REALTYPE
    0.06
    .reduce
    0.06
    Activations Density 0.004%

    No Known Activations