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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7947
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐language code tokens—i.e. bits of code like imports, function definitions, keywords, and other code syntax.

    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
    icrosoft
    -0.08
     ton
    -0.07
    Ben
    -0.06
     Breakfast
    -0.06
    (variable
    -0.06
    セット
    -0.06
     tik
    -0.06
    _Default
    -0.06
     POR
    -0.06
    Contain
    -0.06
    POSITIVE LOGITS
     Forums
    0.06
    392
    0.06
    Place
    0.06
    لة
    0.06
     insulated
    0.06
    anship
    0.06
     _______,
    0.06
    eof
    0.06
    іш
    0.06
    rait
    0.06
    Activations Density 0.008%

    No Known Activations