© 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. 20842
    Prev
    Next
    INDEX
    Explanations

    and

    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
    :request
    -0.06
    (Convert
    -0.06
    752
    -0.06
    Neither
    -0.06
    roy
    -0.06
     nặng
    -0.06
    Editors
    -0.06
    Pack
    -0.06
     самого
    -0.06
    potential
    -0.06
    POSITIVE LOGITS
    зн
    0.07
    ').↵
    0.06
     Κ
    0.06
    .random
    0.06
     masking
    0.06
     сост
    0.06
     Л
    0.06
     pistol
    0.06
    eteor
    0.06
    edení
    0.06
    Activations Density 0.152%

    No Known Activations