© 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. 56192
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    This neuron activates on the questioner’s first‐person introductions of what they’ve done in code (e.g. “I’ve written/created X,” “I have a function that…,” etc.).

    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
     FPGA
    -0.07
    ตลาด
    -0.07
     Rav
    -0.07
     fuzz
    -0.06
     Rodrig
    -0.06
     literature
    -0.06
     CVE
    -0.06
     Falk
    -0.06
     Dead
    -0.06
    GLIGENCE
    -0.06
    POSITIVE LOGITS
    cookies
    0.06
    за
    0.06
    .Integer
    0.06
    rix
    0.06
    /es
    0.06
    れば
    0.06
     المش
    0.06
     ماي
    0.06
    ,event
    0.06
    щее
    0.06
    Activations Density 0.075%

    No Known Activations