© 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 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. 15-RESID-POST-AA
    11. 20996
    Prev
    Next
    INDEX
    Explanations

    getting caught

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     학교
    -0.07
    .chars
    -0.06
    erin
    -0.06
     bakımından
    -0.06
    抱
    -0.06
    edl
    -0.06
    ansas
    -0.06
    maması
    -0.06
    -blocking
    -0.06
     hayır
    -0.06
    POSITIVE LOGITS
    <Group
    0.06
     mv
    0.06
    882
    0.06
     �
    0.06
    结
    0.06
     demographics
    0.06
    _option
    0.06
    ;↵↵↵↵
    0.06
     lunch
    0.06
    ;',↵
    0.06
    Activations Density 0.098%

    No Known Activations