© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 124769
    Prev
    Next
    INDEX
    Explanations

    resumes/CVs

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on standard résumé section headings and related metadata (e.g. “Professional Experience,” company names, dates/titles), i.e. it’s detecting resume structure elements.

    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
    .rb
    -0.07
    posure
    -0.07
    �
    -0.06
     リ
    -0.06
    二人
    -0.06
     댓글
    -0.06
    讓
    -0.06
    „A
    -0.06
     trivia
    -0.06
    	buttons
    -0.06
    POSITIVE LOGITS
    omination
    0.06
    fresh
    0.06
     cons
    0.06
     Modifications
    0.06
    @@@@
    0.06
     thematic
    0.06
     tenant
    0.06
     modification
    0.06
    ensagem
    0.06
    進行
    0.06
    Activations Density 0.011%

    No Known Activations