© 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. 7020
    Prev
    Next
    INDEX
    Explanations

    J

    np_max-act · gemini-2.0-flash

    concepts and terminology related to DNA repair mechanisms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on technical mentions of DNA double‐strand break repair pathways—particularly end‐joining mechanisms like NHEJ or microhomology‐mediated end joining.

    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
     Zealand
    -0.07
    VectorXd
    -0.07
     уровня
    -0.06
     FML
    -0.06
     dine
    -0.06
    	void
    -0.06
     Supplements
    -0.06
     Roma
    -0.06
     beri
    -0.06
    Thomas
    -0.06
    POSITIVE LOGITS
     ваг
    0.07
     sai
    0.07
    تبر
    0.07
    ประกอบ
    0.06
    possible
    0.06
    او
    0.06
     acompan
    0.06
    .alt
    0.06
    Places
    0.06
    Cfg
    0.06
    Activations Density 0.001%

    No Known Activations