© 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. 74059
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects common English derivational suffixes (like ­ity, ­ant, ­ed, ­ing, ­ers) at the ends of words.

    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
     Alzheimer
    -0.06
     demol
    -0.06
     presup
    -0.06
    。当
    -0.06
     bırak
    -0.06
    付
    -0.06
    ++;
↵
    -0.06
    __(
    -0.06
    amics
    -0.06
     descri
    -0.05
    POSITIVE LOGITS
    ING
    0.07
     Ambient
    0.07
    asured
    0.07
     birlikte
    0.06
    ейчас
    0.06
    _USER
    0.06
     intrusive
    0.06
    IED
    0.06
     pane
    0.06
    VEL
    0.06
    Activations Density 0.141%

    No Known Activations