© 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. 7-RESID-POST-AA
    11. 47626
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    The neuron activates on the token "Be" — i.e., the capitalized "Be" prefix at the start of words.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "../
    -0.07
     rallying
    -0.07
    uong
    -0.07
    وروب
    -0.06
    ristol
    -0.06
    уму
    -0.06
     Larson
    -0.06
     Dalton
    -0.06
    Soon
    -0.06
     lung
    -0.06
    POSITIVE LOGITS
     Be
    0.18
    Be
    0.16
    be
    0.15
     be
    0.14
    BE
    0.14
     BE
    0.13
    -be
    0.12
    .Be
    0.12
    (be
    0.11
    /be
    0.11
    Activations Density 0.040%

    No Known Activations