© 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 EvalsExportsAPI 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. 27-RESID-POST-AA
    11. 99782
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atas
    -0.07
    Dump
    -0.07
    VM
    -0.06
    style
    -0.06
    C
    -0.06
    BOUND
    -0.06
    Sure
    -0.06
    bound
    -0.06
     federally
    -0.06
     cooled
    -0.06
    POSITIVE LOGITS
    (strip
    0.06
     finde
    0.06
    alex
    0.06
    ptrdiff
    0.06
    	left
    0.06
     Wort
    0.06
    ledon
    0.06
    FixedSize
    0.06
     soir
    0.06
    UL
    0.06
    Activations Density 0.015%

    No Known Activations