© 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. 58949
    Prev
    Next
    INDEX
    Explanations

    Class

    np_max-act · gemini-2.0-flash

    programming-related terminology and structures related to software licensing and documentation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron primarily activates on occurrences of the Java “Class” type token (e.g. the keyword Class in field or parameter declarations).

    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
    frared
    -0.07
    (move
    -0.07
     hospitality
    -0.06
     어디
    -0.06
     Operation
    -0.06
    :relative
    -0.06
     баб
    -0.06
     보고
    -0.06
     usleep
    -0.06
     ngũ
    -0.06
    POSITIVE LOGITS
     "'",
    0.07
    fadeIn
    0.06
     Sega
    0.06
    worm
    0.06
    <Class
    0.06
    .dm
    0.06
    illus
    0.06
     sl
    0.06
     Christina
    0.06
     SplashScreen
    0.06
    Activations Density 0.006%

    No Known Activations