© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects the word “incidental” (as in “incidental damages”) in license or disclaimer text.

    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
     Protest
    -0.07
     polarity
    -0.07
     EXIT
    -0.07
    CTRL
    -0.07
     videoer
    -0.06
    OUNTER
    -0.06
     grd
    -0.06
    unity
    -0.06
    Credit
    -0.06
    _KIND
    -0.06
    POSITIVE LOGITS
    рещ
    0.06
     springfox
    0.06
    rapper
    0.06
    lauf
    0.06
     صور
    0.06
    .xlabel
    0.06
    atsapp
    0.06
    _notifications
    0.06
     imageNamed
    0.06
    .experimental
    0.06
    Activations Density 0.001%

    No Known Activations