© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55521
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    The neuron detects numeric or quantitative expressions (numbers, decimal values, and measurements) in the text.

    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
    /activity
    -0.07
     ولد
    -0.07
    oples
    -0.06
    DOMAIN
    -0.06
    ESIS
    -0.06
    Ey
    -0.06
     \$
    -0.06
     masturbation
    -0.06
    roupe
    -0.06
    eldig
    -0.06
    POSITIVE LOGITS
    τι
    0.07
     sal
    0.07
    idata
    0.06
    _BG
    0.06
    "]))↵
    0.06
    _IRQ
    0.06
    �
    0.06
     investigate
    0.06
    수
    0.06
     foto
    0.06
    Activations Density 0.007%

    No Known Activations