© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    bars and restaurants

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting words that name or describe bar‐area furnishings and fixtures—e.g. counters, stools, banquettes, and the bar itself.

    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
     edit
    -0.07
     ctrl
    -0.06
     elm
    -0.06
    김
    -0.06
    bol
    -0.06
    .dispatcher
    -0.06
    _FRE
    -0.06
     Bek
    -0.06
     сем
    -0.06
    亿
    -0.06
    POSITIVE LOGITS
     Catholics
    0.07
    -Line
    0.06
     �
    0.06
     %.
    0.06
     κορ
    0.06
    鼻
    0.06
    :inline
    0.06
    ــــــــ
    0.06
     MX
    0.06
    AYOUT
    0.06
    Activations Density 0.011%

    No Known Activations