© 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. 7-RESID-POST-AA
    11. 114537
    Prev
    Next
    INDEX
    Explanations

    code questions

    np_max-act · gemini-2.0-flash

    It detects technical programming context — tokens that commonly appear in code-related questions and answers.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imu
    -0.07
    พน
    -0.06
    peating
    -0.06
    uppercase
    -0.06
    _caption
    -0.06
    	WebElement
    -0.06
    Titulo
    -0.06
     Haley
    -0.06
    anges
    -0.06
    арч
    -0.06
    POSITIVE LOGITS
     Viet
    0.08
    างว
    0.07
     rápido
    0.06
    -big
    0.06
    มาก
    0.06
    憶
    0.06
    [id
    0.06
    wert
    0.06
    %H
    0.06
    結婚
    0.06
    Activations Density 0.331%

    No Known Activations