© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 90046
    Prev
    Next
    INDEX
    Explanations

    Code/technical specifications

    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
     Esper
    -0.07
     İmpar
    -0.07
     Walton
    -0.07
    нюю
    -0.07
     no
    -0.07
     Rath
    -0.06
     Designs
    -0.06
    (ident
    -0.06
     patents
    -0.06
    vincial
    -0.06
    POSITIVE LOGITS
    large
    0.06
    �
    0.06
     vanilla
    0.06
    emory
    0.06
    �
    0.06
    _quick
    0.06
    öff
    0.06
     đáp
    0.06
    .setY
    0.06
    cke
    0.06
    Activations Density 0.000%

    No Known Activations