© 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. 7-RESID-POST-AA
    11. 42915
    Prev
    Next
    INDEX
    Explanations

    1

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clo
    -0.07
    eya
    -0.07
    -क
    -0.06
     dataset
    -0.06
     dos
    -0.06
    .IsDBNull
    -0.06
     Warfare
    -0.06
     Willow
    -0.06
     col
    -0.06
     coworkers
    -0.06
    POSITIVE LOGITS
     başka
    0.07
    �合
    0.07
    )];↵↵
    0.06
    asia
    0.06
    ecake
    0.06
    .onOptionsItemSelected
    0.06
    注意
    0.06
     داریم
    0.06
     surrendered
    0.06
    PKG
    0.06
    Activations Density 0.003%

    No Known Activations