© 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. 11-RESID-POST-AA
    11. 46140
    Prev
    Next
    INDEX
    Explanations

    registry

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Don
    -0.08
    666
    -0.08
     İl
    -0.07
    795
    -0.07
    .email
    -0.07
     Hil
    -0.07
    Bon
    -0.07
    140
    -0.07
     �
    -0.07
    266
    -0.07
    POSITIVE LOGITS
    Registry
    0.10
     registry
    0.10
     Registry
    0.09
    .Registry
    0.08
    registry
    0.08
     roster
    0.08
    .registry
    0.08
     系
    0.07
    y
    0.07
    _registry
    0.07
    Activations Density 0.002%

    No Known Activations