© 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. 129653
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the “0x” pattern—i.e. hexadecimal literals or tokens beginning with “0x”—throughout code.

    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
    .Window
    -0.07
    изнес
    -0.07
    .tooltip
    -0.07
    Square
    -0.07
     Laboratory
    -0.07
    owan
    -0.06
    (fs
    -0.06
    _spinner
    -0.06
    _old
    -0.06
     setPosition
    -0.06
    POSITIVE LOGITS
    (es
    0.07
     PyObject
    0.07
    ありがとう
    0.06
     groupe
    0.06
     або
    0.06
    Overflow
    0.06
     addr
    0.06
    긔
    0.06
     手机
    0.06
     directives
    0.06
    Activations Density 0.023%

    No Known Activations