© 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. 109141
    Prev
    Next
    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash

    The neuron fires on the opening “You need …” (or similar “You …”) instruction phrases in answers.

    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
     Repeat
    -0.07
     จำ
    -0.07
    *******↵
    -0.07
    ージ
    -0.07
    ellers
    -0.07
    -modal
    -0.06
     Hansen
    -0.06
     PdfPCell
    -0.06
     dispens
    -0.06
    Meal
    -0.06
    POSITIVE LOGITS
    lij
    0.06
    :h
    0.06
    .ll
    0.06
    Aff
    0.06
    197
    0.06
    BR
    0.06
    AW
    0.06
     vrouwen
    0.06
     shark
    0.06
    _gr
    0.06
    Activations Density 0.028%

    No Known Activations