© 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. 23-RESID-POST-AA
    11. 8131
    Prev
    Next
    INDEX
    Explanations

    Chris

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uild
    -0.06
     Lia
    -0.06
     fut
    -0.06
    inventory
    -0.06
    归
    -0.06
     tvor
    -0.06
     licked
    -0.06
     TextArea
    -0.06
     Strauss
    -0.06
    stdarg
    -0.05
    POSITIVE LOGITS
    /of
    0.08
     Judaism
    0.07
    ensation
    0.07
     Quote
    0.07
     먼저
    0.06
     Script
    0.06
     PdfPCell
    0.06
    ONDON
    0.06
    mapping
    0.06
    Validators
    0.06
    Activations Density 0.001%

    No Known Activations