© 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. 121505
    Prev
    Next
    INDEX
    Explanations

    grid

    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
     molecule
    -0.07
    n
    -0.06
     milestone
    -0.06
    Doctors
    -0.06
    	option
    -0.06
    undred
    -0.06
     Exped
    -0.06
    ilestone
    -0.06
    ан
    -0.06
     która
    -0.05
    POSITIVE LOGITS
    grid
    0.21
    Grid
    0.13
    .grid
    0.12
     Grid
    0.11
    -grid
    0.11
    GRID
    0.11
    (grid
    0.10
    .Grid
    0.09
    _grid
    0.09
    (Grid
    0.08
    Activations Density 0.005%

    No Known Activations