© 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 EvalsExportsAPI 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. 38098
    Prev
    Next
    INDEX
    Explanations

    Allowable, meeting requirements

    np_max-act · gemini-2.0-flash

    technical specifications and details specific to electronic devices and systems.

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

    The neuron fires on evaluative adjectives and adverbs (like “critical,” “acceptable,” “fine,” “great”) that qualify technical descriptions.

    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
    ذكر
    -0.07
    ίσω
    -0.07
    unun
    -0.06
    .Scale
    -0.06
     Dann
    -0.06
     Barnes
    -0.06
    izace
    -0.06
    larıyla
    -0.06
     Granny
    -0.06
    oward
    -0.06
    POSITIVE LOGITS
    (pb
    0.07
    173
    0.07
    각
    0.07
    ajs
    0.06
    ={
    0.06
    едь
    0.06
     generally
    0.06
    .appcompat
    0.06
    ۱۱
    0.06
    _slide
    0.06
    Activations Density 0.031%

    No Known Activations