© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14021
    Prev
    Next
    INDEX
    Explanations

    limits/conditions/regard

    np_max-act · gemini-2.0-flash

    The neuron fires on comparative or degree‐marking phrases—especially constructions like “as far as…” or “in the way of…” that signal extent or proportion.

    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
    _outline
    -0.07
     �
    -0.06
    кувати
    -0.06
    neh
    -0.06
    PerPixel
    -0.06
     povin
    -0.06
     Impress
    -0.06
    هن
    -0.06
    igsaw
    -0.06
    ührung
    -0.06
    POSITIVE LOGITS
    \Json
    0.07
    Als
    0.06
    $(".
    0.06
     biện
    0.06
     wereld
    0.06
     useState
    0.06
    询
    0.06
     chy
    0.06
    ımda
    0.06
    ALLERY
    0.06
    Activations Density 0.087%

    No Known Activations