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

    Neuronpedia

    Jacobian LensNEW
    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. 38004
    Prev
    Next
    INDEX
    Explanations

    show

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs and verb‐phrases that signal emphasis or draw attention (e.g. “raises,” “shows,” “illustrate,” “highlights,” “brought attention to”).

    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
     Lakes
    -0.06
     radiant
    -0.06
    andatory
    -0.06
     discomfort
    -0.06
    236
    -0.06
     Php
    -0.06
     deposits
    -0.06
     suffix
    -0.06
    Unknown
    -0.06
    (':')[
    -0.06
    POSITIVE LOGITS
     personalized
    0.07
     finans
    0.06
     initialised
    0.06
     reminding
    0.06
     displaying
    0.06
    printed
    0.06
    NavigatorMove
    0.06
    ład
    0.06
     illuminate
    0.06
    metro
    0.06
    Activations Density 0.046%

    No Known Activations