© 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. 110506
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is triggered by C++/Java‐style generic or template type declarations and angle‐bracket constructs (e.g. the “template<…>”, “typename”/“<T>” patterns).

    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
     Killed
    -0.06
     cru
    -0.06
    Clar
    -0.06
     вже
    -0.06
     intercept
    -0.06
    isEnabled
    -0.06
     darkness
    -0.06
    kir
    -0.06
    .Unique
    -0.06
     tween
    -0.06
    POSITIVE LOGITS
     бюджет
    0.07
     준
    0.07
    ULSE
    0.07
    ле
    0.06
     annoy
    0.06
    =<?
    0.06
    getService
    0.06
     Saul
    0.06
     ジ
    0.06
    �
    0.06
    Activations Density 0.120%

    No Known Activations