© 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. 58403
    Prev
    Next
    INDEX
    Explanations

    Legal/Legislative sections

    np_max-act · gemini-2.0-flash

    This neuron detects legal references and section numbers (e.g., statute citations and numeric subsection markers).

    oai_token-act-pair · o4-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
    ált
    -0.07
    723
    -0.07
    ेब
    -0.07
     condom
    -0.06
    .scalablytyped
    -0.06
     compromising
    -0.06
    esk
    -0.06
    �
    -0.06
     systém
    -0.06
    Host
    -0.06
    POSITIVE LOGITS
     ні
    0.06
    挑
    0.06
    leich
    0.06
     مرگ
    0.06
    ensored
    0.06
    <tag
    0.06
     самое
    0.06
    (recipe
    0.06
    (EFFECT
    0.06
    -paced
    0.06
    Activations Density 0.016%

    No Known Activations