© 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. 54266
    Prev
    Next
    INDEX
    Explanations

    pause

    np_max-act · gemini-2.0-flash

    segments of code that involve memory management and object deletion.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on tokens associated with pausing or waiting for user input (e.g. “pause,” “Press ‘Return’,” cin.get(), cin.ignore(), etc.).

    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
     Twe
    -0.07
    thes
    -0.07
    목
    -0.06
    .level
    -0.06
     Creates
    -0.06
    แ
    -0.06
    enerator
    -0.06
     slogan
    -0.06
    TES
    -0.06
    단
    -0.06
    POSITIVE LOGITS
     صور
    0.07
     glanced
    0.07
    ━
    0.07
    .urls
    0.06
     спост
    0.06
    _smart
    0.06
     unite
    0.06
    -navigation
    0.06
    aincontri
    0.06
    ="<?=$
    0.06
    Activations Density 0.002%

    No Known Activations