© 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. 89585
    Prev
    Next
    INDEX
    Explanations

    sports transfers

    np_max-act · gemini-2.0-flash

    The neuron fires on terms describing player transfers and contract moves (e.g. signed, joined, loan, deal, contract, option).

    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
    _inner
    -0.08
     painter
    -0.07
    spoken
    -0.07
    札
    -0.06
    .shared
    -0.06
    Suite
    -0.06
    otoxic
    -0.06
    覺
    -0.06
    ability
    -0.06
    ukes
    -0.06
    POSITIVE LOGITS
    bulk
    0.07
     Lionel
    0.06
    pecially
    0.06
    	Default
    0.06
     چرا
    0.06
    (indent
    0.06
     όπου
    0.06
     Nepal
    0.06
    Contents
    0.06
    šť
    0.06
    Activations Density 0.022%

    No Known Activations