© 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. 126606
    Prev
    Next
    INDEX
    Explanations

    Crimes

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—especially standalone numbers, decimal fractions, ages, dates, and similar numeric expressions.

    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
     training
    -0.07
    Training
    -0.07
     norm
    -0.07
    set
    -0.06
    keyword
    -0.06
    Subviews
    -0.06
     hybrid
    -0.06
     efficient
    -0.06
     casts
    -0.06
    แ
    -0.06
    POSITIVE LOGITS
     تشکیل
    0.07
    gis
    0.06
    �n
    0.06
     Moderate
    0.06
     територ
    0.06
    %;">↵
    0.06
    contres
    0.06
    _IRQHandler
    0.06
    _deploy
    0.06
    δοση
    0.06
    Activations Density 0.011%

    No Known Activations