© 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. 56122
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    This neuron spots the boilerplate “file that was distributed with this source code” phrase (i.e. license‐header text) in code comments.

    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
    #!
    -0.07
     takový
    -0.06
    _gradient
    -0.06
     weiber
    -0.06
    	On
    -0.06
    �
    -0.06
    ','#
    -0.06
    feed
    -0.06
     inund
    -0.06
     >::
    -0.06
    POSITIVE LOGITS
    _mul
    0.08
     Recognition
    0.07
     which
    0.07
    .Role
    0.06
     disciplinary
    0.06
     YT
    0.06
     wei
    0.06
    issen
    0.06
    _che
    0.06
    Want
    0.06
    Activations Density 0.002%

    No Known Activations