© 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. 92313
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron fires on the boilerplate phrase that introduces license terms—especially occurrences of “this list of conditions (and the following disclaimer)” in copyright headers.

    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
    FR
    -0.06
     Associations
    -0.06
    olen
    -0.06
    ART
    -0.06
     Observatory
    -0.06
     Ded
    -0.06
    likes
    -0.05
    тож
    -0.05
    shaw
    -0.05
     Fif
    -0.05
    POSITIVE LOGITS
    SQLException
    0.07
    _DF
    0.07
    <Object
    0.07
    -rounded
    0.07
     CentOS
    0.06
    .toDouble
    0.06
    ?’
    0.06
    -regexp
    0.06
    .indexOf
    0.06
    (environment
    0.06
    Activations Density 0.002%

    No Known Activations