© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 100321
    Prev
    Next
    INDEX
    Explanations

    film awards

    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
    (plan
    -0.07
     pearls
    -0.07
     observe
    -0.07
    yme
    -0.07
     Uz
    -0.07
     infinitely
    -0.07
     pup
    -0.07
     văn
    -0.07
     recru
    -0.06
     sacred
    -0.06
    POSITIVE LOGITS
    avigator
    0.07
    =http
    0.06
     cancelButtonTitle
    0.06
    arefa
    0.06
     гри
    0.06
    ObjectOfType
    0.05
     Alan
    0.05
     Hitler
    0.05
    pesan
    0.05
    aroo
    0.05
    Activations Density 0.015%

    No Known Activations