© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109216
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens representing floating-point decimal fractions (e.g., “3.1875,” “0.395751953125,” etc.).

    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
    -largest
    -0.07
    스
    -0.07
     inexpensive
    -0.06
     №
    -0.06
     very
    -0.06
    FLASH
    -0.06
    Fal
    -0.06
     exceeds
    -0.06
    SKI
    -0.06
    craft
    -0.06
    POSITIVE LOGITS
    :.
    0.07
    iệp
    0.07
     �
    0.06
    dhcp
    0.06
    ">'
    0.06
    |[
    0.06
    ственным
    0.06
    	connection
    0.06
     Sanct
    0.06
     pkg
    0.06
    Activations Density 0.031%

    No Known Activations