© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 45080
    Prev
    Next
    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash

    The neuron activates on speaker‐label tokens (e.g. “Person,” numeric IDs like “2,” and related markers) indicating who is speaking.

    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
     apology
    -0.07
     XCTAssertEqual
    -0.07
     market
    -0.07
     testData
    -0.07
    _lex
    -0.07
    -0.07
    通過
    -0.07
    +"\
    -0.07
    ligne
    -0.06
     year
    -0.06
    POSITIVE LOGITS
     predicates
    0.07
     běž
    0.07
     Johnston
    0.07
     summar
    0.06
     initialization
    0.06
     Blond
    0.06
     flashed
    0.06
     şans
    0.06
     Ahmet
    0.06
    ��
    0.05
    Activations Density 0.029%

    No Known Activations