© 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. 46849
    Prev
    Next
    INDEX
    Explanations

    Calling police/emergency services

    np_max-act · gemini-2.0-flash

    words associated with violent crimes and legal proceedings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    經
    -0.07
    経
    -0.06
    ()/
    -0.06
     traged
    -0.06
    やす
    -0.06
     beautifully
    -0.06
     เก
    -0.06
    風
    -0.06
     ahead
    -0.06
    rete
    -0.06
    POSITIVE LOGITS
    .guild
    0.06
    _Parse
    0.06
    _is
    0.06
    圭圭
    0.06
    (ConfigurationManager
    0.06
     医
    0.06
    .indent
    0.06
     outsider
    0.06
    ypes
    0.06
    220
    0.06
    Activations Density 0.017%

    No Known Activations