© 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. 92115
    Prev
    Next
    INDEX
    Explanations

    endings

    np_max-act · gemini-2.0-flash

    This neuron fires on time-related qualifiers—especially hyphenated schedule or commitment terms like “full-time” or similar words indicating regularity.

    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
    gay
    -0.07
     fro
    -0.06
     approaches
    -0.06
    gte
    -0.06
     Mik
    -0.06
     walmart
    -0.06
    Mom
    -0.06
    mom
    -0.06
     pert
    -0.06
     Urb
    -0.06
    POSITIVE LOGITS
    _pref
    0.07
    _Native
    0.07
     Omega
    0.07
    {/
    0.07
    었다
    0.06
    ایش
    0.06
     javafx
    0.06
    iến
    0.06
    _script
    0.06
    άζ
    0.06
    Activations Density 0.137%

    No Known Activations