© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 115216
    Prev
    Next
    INDEX
    Explanations

    by

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    保持
    -0.07
    terminal
    -0.06
    SPACE
    -0.06
     Wind
    -0.06
     intervening
    -0.06
     valves
    -0.06
     concentrating
    -0.06
     Change
    -0.06
    osen
    -0.06
     dubbed
    -0.06
    POSITIVE LOGITS
    (NO
    0.07
    \Php
    0.06
    0.06
    енты
    0.06
     student
    0.06
     overseas
    0.06
    267
    0.06
    =[[
    0.06
     ап
    0.06
     deportation
    0.06
    Activations Density 0.016%

    No Known Activations