© 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. 19-RESID-POST-AA
    11. 113213
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    -gun
    -0.06
     öğ
    -0.06
     перен
    -0.06
     المست
    -0.06
     establishment
    -0.06
     Torrent
    -0.06
    Larry
    -0.06
    sound
    -0.06
     remedy
    -0.06
     remains
    -0.06
    POSITIVE LOGITS
    (letter
    0.07
     الى
    0.06
    ilers
    0.06
     Pessoa
    0.06
    Deck
    0.06
     getDefault
    0.06
    (Screen
    0.06
    bones
    0.06
     faults
    0.06
     Canton
    0.06
    Activations Density 0.020%

    No Known Activations