© 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. 91088
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    This neuron activates on negation tokens (e.g., “not,” “aren’t,” “isn’t”).

    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
    ायत
    -0.07
    Зап
    -0.07
    ській
    -0.06
    NotificationCenter
    -0.06
     BorderSide
    -0.06
     disponibles
    -0.06
     Ấn
    -0.06
    居
    -0.06
    _TWO
    -0.06
    iji
    -0.06
    POSITIVE LOGITS
     Transformer
    0.07
     delet
    0.07
    _internal
    0.07
    kinson
    0.07
     prohibits
    0.06
     framework
    0.06
    _HAVE
    0.06
     â
    0.06
     quat
    0.06
     latent
    0.06
    Activations Density 0.010%

    No Known Activations