© 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. 128371
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting conditional instruction phrases that begin with “if you,” i.e. the “if you…” pattern in comments or 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
    ynam
    -0.08
    /copyleft
    -0.07
     wait
    -0.06
    osals
    -0.06
    ,他
    -0.06
     periods
    -0.06
     could
    -0.06
    igma
    -0.06
    »)
    -0.06
    话
    -0.06
    POSITIVE LOGITS
     pentru
    0.07
    stvo
    0.06
     toggle
    0.06
    ?><?
    0.06
    ,(
    0.06
    .getMin
    0.06
    /navbar
    0.06
    Click
    0.06
    итися
    0.06
    .hover
    0.06
    Activations Density 0.023%

    No Known Activations