© 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. 7130
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs and associated prepositions that describe a footballer’s club transfers or signings (e.g. “moved from…to…,” “signed for…,” “joined…”).

    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
    #if
    -0.07
     thắng
    -0.06
    .detach
    -0.06
     part
    -0.06
     test
    -0.06
    	light
    -0.06
    _block
    -0.06
    ์อ
    -0.05
    лож
    -0.05
    	req
    -0.05
    POSITIVE LOGITS
     rut
    0.07
    Chat
    0.07
    .GET
    0.07
     Gaz
    0.07
    yses
    0.07
     JAXB
    0.06
     Virt
    0.06
     AGE
    0.06
    categoria
    0.06
     abre
    0.06
    Activations Density 0.009%

    No Known Activations