© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108797
    Prev
    Next
    INDEX
    Explanations

    bamboo

    np_max-act · gemini-2.0-flash

    The neuron is specialized to spot occurrences of the word “bamboo.”

    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
     Pad
    -0.07
     nausea
    -0.06
    drivers
    -0.06
    _training
    -0.06
    郭
    -0.06
     Mourinho
    -0.06
    Lewis
    -0.06
     ذكر
    -0.06
    _guard
    -0.06
     yüzyıl
    -0.06
    POSITIVE LOGITS
     bamboo
    0.10
     Bamboo
    0.10
     redefine
    0.07
     препараты
    0.07
    ANTITY
    0.06
    Assignment
    0.06
    divide
    0.06
     Tunnel
    0.06
     tunnel
    0.06
    assandra
    0.06
    Activations Density 0.006%

    No Known Activations