© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron activates on the selected answer option—specifically the token “Yes.”

    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
     unknow
    -0.08
    xm
    -0.07
    弱
    -0.06
     FDA
    -0.06
     нельзя
    -0.06
     önceki
    -0.06
     existence
    -0.06
     опис
    -0.06
    issors
    -0.06
    やる
    -0.06
    POSITIVE LOGITS
    .chapter
    0.07
    iring
    0.07
     Southeast
    0.06
    usta
    0.06
    _Send
    0.06
     consolid
    0.06
     disin
    0.06
    _runs
    0.06
    .chomp
    0.06
    .Font
    0.06
    Activations Density 0.001%

    No Known Activations