© 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. 27-RESID-POST-AA
    11. 22788
    Prev
    Next
    INDEX
    Explanations

    legal/formal language

    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
     obstacle
    -0.07
     peas
    -0.06
    .Pr
    -0.06
     football
    -0.06
     Prep
    -0.06
     jaw
    -0.06
     Income
    -0.06
     shook
    -0.06
    pressure
    -0.06
     seeds
    -0.06
    POSITIVE LOGITS
    _PS
    0.07
    zych
    0.07
    *ft
    0.07
     currentPosition
    0.06
    bdd
    0.06
    dives
    0.06
    _GENER
    0.06
    ajo
    0.06
     Collect
    0.06
    ΜΠ
    0.06
    Activations Density 0.053%

    No Known Activations