© 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. 15-RESID-POST-AA
    11. 111583
    Prev
    Next
    INDEX
    Explanations

    academic papers and research

    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
    876
    -0.07
    偏
    -0.06
    crement
    -0.06
     konum
    -0.06
     drastically
    -0.06
     міль
    -0.06
    كال
    -0.06
    @"
    -0.06
    径
    -0.06
     relative
    -0.06
    POSITIVE LOGITS
    퓨터
    0.06
     Jab
    0.06
     США
    0.06
    .MouseAdapter
    0.06
     худож
    0.06
    irty
    0.06
     chiế
    0.06
    汽车
    0.06
    �력
    0.06
    ex
    0.06
    Activations Density 0.192%

    No Known Activations