© 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. 65461
    Prev
    Next
    INDEX
    Explanations

    -terminal

    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
     flag
    -0.07
     air
    -0.06
    ация
    -0.06
     thanks
    -0.06
     Sunset
    -0.06
    Thanks
    -0.06
    ASE
    -0.06
     white
    -0.06
    (pred
    -0.06
     Santo
    -0.06
    POSITIVE LOGITS
    -terminal
    0.07
    aptop
    0.06
    提出
    0.06
    ymce
    0.06
    estination
    0.06
    .backend
    0.06
    cntl
    0.06
    ricanes
    0.06
     GFP
    0.06
    reon
    0.06
    Activations Density 0.003%

    No Known Activations