© 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. 54542
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash

    This neuron detects discourse-transition words or phrases (e.g. “In addition,” “However,”) that signal shifts or connectors in the text.

    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
     Trek
    -0.07
    _IF
    -0.07
    _DST
    -0.06
     PERSON
    -0.06
    Additionally
    -0.06
     '}↵
    -0.06
    PRETTY
    -0.06
     Shim
    -0.06
     inquire
    -0.06
     DONE
    -0.06
    POSITIVE LOGITS
     جهانی
    0.07
     delegation
    0.07
     stagger
    0.06
     subscript
    0.06
     Phương
    0.06
     province
    0.06
    ),$
    0.06
    menus
    0.06
    екси
    0.06
    export
    0.06
    Activations Density 0.566%

    No Known Activations