© 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. 110491
    Prev
    Next
    INDEX
    Explanations

    para

    np_max-act · gemini-2.0-flash

    The neuron flags Portuguese-language function or content words—i.e. it activates on Portuguese 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
    on
    -0.09
    OW
    -0.08
    ow
    -0.07
    _os
    -0.07
    row
    -0.07
    CK
    -0.07
    ock
    -0.07
    ck
    -0.07
     on
    -0.07
    SON
    -0.07
    POSITIVE LOGITS
     para
    0.13
     Para
    0.10
     PARA
    0.09
     to
    0.09
    Para
    0.09
     TO
    0.09
    обще
    0.08
     To
    0.08
    liğine
    0.08
     Marc
    0.07
    Activations Density 0.071%

    No Known Activations