© 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. 11-RESID-POST-AA
    11. 49417
    Prev
    Next
    INDEX
    Explanations

    in

    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
     voluntarily
    -0.08
    -store
    -0.08
    Foot
    -0.07
    voke
    -0.07
    ollo
    -0.07
     collectors
    -0.07
     otra
    -0.07
    >Your
    -0.07
     allo
    -0.06
    mployee
    -0.06
    POSITIVE LOGITS
     in
    0.29
     In
    0.26
     IN
    0.23
    In
    0.23
    in
    0.22
    -in
    0.21
     in
    0.19
    IN
    0.18
    —in
    0.18
    _IN
    0.17
    Activations Density 1.337%

    No Known Activations