© 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. 19-RESID-POST-AA
    11. 84320
    Prev
    Next
    INDEX
    Explanations

    Directorate

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    losti
    -0.06
     exhibitions
    -0.06
    multiline
    -0.06
     heal
    -0.06
    amenti
    -0.06
    _supp
    -0.06
    盖
    -0.06
    ？”
    -0.06
    Animal
    -0.06
    _nil
    -0.06
    POSITIVE LOGITS
    UNS
    0.07
     Com
    0.07
     Bone
    0.07
    ,+
    0.07
    ム
    0.06
    .isConnected
    0.06
     homeland
    0.06
    (field
    0.06
     Bliss
    0.06
     Superintendent
    0.06
    Activations Density 0.000%

    No Known Activations