© 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. 3-RESID-POST-AA
    11. 123267
    Prev
    Next
    INDEX
    Explanations

    ex

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oun
    -0.06
    umph
    -0.06
     Injector
    -0.06
    Assertions
    -0.06
    tid
    -0.06
    alleng
    -0.06
    iteit
    -0.06
     praising
    -0.06
     RecognitionException
    -0.05
    ulen
    -0.05
    POSITIVE LOGITS
    ex
    0.10
    EX
    0.08
     वजह
    0.08
     verwendet
    0.07
     düşün
    0.07
     LEFT
    0.07
    _HEX
    0.07
    DTD
    0.07
    ระบบ
    0.07
     getenv
    0.07
    Activations Density 0.003%

    No Known Activations