© 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. 108902
    Prev
    Next
    INDEX
    Explanations

    foundation

    np_max-act · gemini-2.0-flash

    The neuron fires on words that denote beginnings or foundations—terms like “entry point,” “preparatory,” “groundwork,” and “foundation.”

    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
    ideshow
    -0.07
    _request
    -0.07
     login
    -0.07
    軟
    -0.06
     Beer
    -0.06
    .gradle
    -0.06
     tagName
    -0.06
     voyeur
    -0.06
    	cursor
    -0.06
    NotExist
    -0.06
    POSITIVE LOGITS
     Throwable
    0.06
    ?>/
    0.06
     BaseController
    0.06
     DRV
    0.06
    แนะนำ
    0.06
     Chiefs
    0.06
    dělení
    0.06
    ΑΛ
    0.06
     Calc
    0.06
    <LM
    0.06
    Activations Density 0.059%

    No Known Activations