Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 83479
    Prev
    Next
    INDEX
    Explanations

    Kendall

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brittany
    -0.07
     ix
    -0.06
    batis
    -0.06
    Dto
    -0.06
     frightened
    -0.06
     seab
    -0.06
    latlong
    -0.06
     tấn
    -0.06
     Night
    -0.06
    CreateTime
    -0.06
    POSITIVE LOGITS
     Kendall
    0.08
    play
    0.07
    اضر
    0.07
    ensual
    0.07
    út
    0.06
     Lindsey
    0.06
     dosp
    0.06
     бух
    0.06
    弘
    0.06
     Basic
    0.06
    Activations Density 0.002%

    No Known Activations