© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92129
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    fragments of code that define data structures with specific validation attributes in programming languages, particularly for user inputs.

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

    This neuron detects numeric literals written with a decimal point (floating‐point numbers).

    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
    hatt
    -0.06
    CPF
    -0.06
    UZ
    -0.06
     PSU
    -0.06
     Congressional
    -0.06
     Penn
    -0.06
    .En
    -0.06
    atinum
    -0.06
    되
    -0.06
    Con
    -0.06
    POSITIVE LOGITS
     denotes
    0.07
    >').
    0.06
    .Args
    0.06
     tons
    0.06
    iped
    0.06
    Editor
    0.06
     Effects
    0.06
    _seg
    0.06
     announcing
    0.06
     захист
    0.06
    Activations Density 0.059%

    No Known Activations