© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23-RESID-POST-AA
    11. 69164
    Prev
    Next
    INDEX
    Explanations

    say "a" or "an"

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     diesel
    -0.08
    entialAction
    -0.07
    	Con
    -0.06
    31
    -0.06
    	B
    -0.06
     offseason
    -0.06
    uptools
    -0.06
    _almost
    -0.06
     designated
    -0.06
     ordinance
    -0.06
    POSITIVE LOGITS
    طي
    0.07
    slashes
    0.06
    fee
    0.06
    PIPE
    0.06
     Moms
    0.06
    rant
    0.06
    crafted
    0.06
    okud
    0.06
    agg
    0.06
    чень
    0.06
    Activations Density 0.254%

    No Known Activations