© 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. 54511
    Prev
    Next
    INDEX
    Explanations

    Acronyms

    np_max-act · gemini-2.0-flash

    The neuron predominantly detects short uppercase abbreviations or acronyms (e.g. two‐ or three‐letter all-caps terms).

    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
     waitress
    -0.07
     sensit
    -0.06
    incorrect
    -0.06
    conciliation
    -0.06
     chạy
    -0.06
     deriv
    -0.06
    反应
    -0.06
    ै↵
    -0.06
    бач
    -0.06
     Saturday
    -0.06
    POSITIVE LOGITS
    .Formatting
    0.06
    .ke
    0.06
    Gain
    0.06
     Finished
    0.06
    =<?
    0.06
    '=>['
    0.06
     NGX
    0.06
     sklearn
    0.06
    すぐ
    0.06
     http
    0.06
    Activations Density 0.023%

    No Known Activations