© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 11838
    Prev
    Next
    INDEX
    Explanations

    /http

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     produto
    -0.06
     Sexual
    -0.06
     DATE
    -0.06
     muchos
    -0.06
     Teeth
    -0.06
     blockade
    -0.06
    acidad
    -0.06
     genitals
    -0.06
    Sales
    -0.06
     tratamiento
    -0.06
    POSITIVE LOGITS
    fon
    0.07
    .Ap
    0.07
    -a
    0.07
    /il
    0.07
    την
    0.07
     Matth
    0.07
     kok
    0.07
     суспіль
    0.06
    collectionView
    0.06
     //////////////////////////////////
    0.06
    Activations Density 0.001%

    No Known Activations