© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 95548
    Prev
    Next
    INDEX
    Explanations

    Names and places

    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
    374
    -0.07
     depicted
    -0.06
    ована
    -0.06
     veterinary
    -0.06
    410
    -0.06
     goats
    -0.06
     programming
    -0.06
     tensor
    -0.06
     €
    -0.06
    (TABLE
    -0.06
    POSITIVE LOGITS
     Dy
    0.17
     Dylan
    0.11
     DY
    0.10
     dy
    0.10
    DY
    0.08
    y
    0.08
    ys
    0.07
    .dy
    0.07
    (dy
    0.07
    YG
    0.07
    Activations Density 0.012%

    No Known Activations