© 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. 29654
    Prev
    Next
    INDEX
    Explanations

    AT

    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
     sorting
    -0.06
    Voice
    -0.06
     Non
    -0.06
    Non
    -0.06
    ometric
    -0.06
    ($("#
    -0.06
    clang
    -0.06
    emiz
    -0.06
     prototype
    -0.06
    ijkstra
    -0.06
    POSITIVE LOGITS
     Moines
    0.08
    (platform
    0.07
     ClassNotFoundException
    0.06
     نگهد
    0.06
    (guild
    0.06
     yeterli
    0.06
     لها
    0.06
    ximo
    0.06
     acknowled
    0.06
     consequ
    0.06
    Activations Density 0.001%

    No Known Activations