© 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 EvalsExportsinterp-engineNEWAPI 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. 35262
    Prev
    Next
    INDEX
    Explanations

    data tables

    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
    行动
    -0.07
    .de
    -0.06
     Listen
    -0.06
     tenants
    -0.06
     recorded
    -0.06
     interruption
    -0.06
    	copy
    -0.06
    'user
    -0.06
     Serif
    -0.06
     Cree
    -0.06
    POSITIVE LOGITS
     qs
    0.07
    presence
    0.06
    .GL
    0.06
    坏
    0.06
    _BOOL
    0.06
    ION
    0.06
     wins
    0.06
     Ukrain
    0.06
    .CodeAnalysis
    0.06
    ovně
    0.06
    Activations Density 0.012%

    No Known Activations