© 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. 15-RESID-POST-AA
    11. 27740
    Prev
    Next
    INDEX
    Explanations

    A

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ern
    -0.10
    nection
    -0.07
     ro
    -0.07
    .getLeft
    -0.07
    aty
    -0.06
    .G
    -0.06
    rado
    -0.06
    έντ
    -0.06
     Nice
    -0.06
     summon
    -0.06
    POSITIVE LOGITS
    (Job
    0.06
     obě
    0.06
     workplaces
    0.06
    �
    0.06
     nebezpeč
    0.06
    >'
↵
    0.06
    .DataAccess
    0.06
     Nina
    0.05
     블
    0.05
     Bill
    0.05
    Activations Density 0.000%

    No Known Activations