© 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. 127064
    Prev
    Next
    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    The neuron activates on sentence‐initial tokens—especially capitalized transition words (e.g. “In,” “Next,” “This,” “That’s”) that start new sentences.

    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
     mockery
    -0.07
     EN
    -0.07
    _FINAL
    -0.06
    (){}↵
    -0.06
     быть
    -0.06
     coupling
    -0.06
    ________________________________________________________________
    -0.06
     +
    ↵
    -0.06
     peanut
    -0.06
    .weixin
    -0.06
    POSITIVE LOGITS
     клуб
    0.07
    既
    0.06
    stdafx
    0.06
     titular
    0.06
    ‰
    0.06
     Prahy
    0.06
     непосред
    0.06
    ヾ
    0.06
     Dickinson
    0.06
     kodu
    0.06
    Activations Density 0.192%

    No Known Activations