© 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. 11-RESID-POST-AA
    11. 101768
    Prev
    Next
    INDEX
    Explanations

    Code

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    R
    -0.06
     hackers
    -0.06
    enarios
    -0.06
     storage
    -0.06
    東京
    -0.06
    emez
    -0.06
    r
    -0.06
     werde
    -0.06
    стория
    -0.06
    ýv
    -0.06
    POSITIVE LOGITS
     INSTANCE
    0.07
    ,L
    0.06
    <Mesh
    0.06
     Lump
    0.06
    afil
    0.06
    瞬
    0.06
    aves
    0.06
    antro
    0.06
     �
    0.06
     구
    0.06
    Activations Density 0.027%

    No Known Activations