© 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. 19-RESID-POST-AA
    11. 86993
    Prev
    Next
    INDEX
    Explanations

    Metrics and statistics

    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
    _then
    -0.08
    ende
    -0.07
    ์การ
    -0.06
    >window
    -0.06
     enum
    -0.06
    rapy
    -0.06
    strpos
    -0.06
    Nhap
    -0.06
    CAL
    -0.06
     poetry
    -0.06
    POSITIVE LOGITS
     monitor
    0.07
    さんが
    0.07
     monitors
    0.06
    Ag
    0.06
     ApplicationController
    0.06
     chic
    0.06
     blat
    0.06
     medications
    0.06
     Erdogan
    0.06
    �
    0.05
    Activations Density 0.221%

    No Known Activations