© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 89202
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on attorney‐attribution lines—i.e. the names, titles, and office affiliations of lawyers and their “for Plaintiff/for Defendant” labels.

    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
    _CHUNK
    -0.06
    rectangle
    -0.06
    ":{↵
    -0.06
    _plate
    -0.06
     quality
    -0.06
    qi
    -0.06
    /day
    -0.06
     scream
    -0.06
     unnecessary
    -0.06
     vagina
    -0.06
    POSITIVE LOGITS
    preserve
    0.08
    领导
    0.07
     Prototype
    0.06
     RHS
    0.06
    php
    0.06
    _result
    0.06
    　�
    0.06
     uzav
    0.06
     OPP
    0.06
    0.06
    Activations Density 0.013%

    No Known Activations