© 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. 73865
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that introduce numeric quantities or ranges (e.g. “from,” “day,” measurement contexts).

    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
     chung
    -0.06
     leopard
    -0.06
    (Be
    -0.06
     gameplay
    -0.06
    aning
    -0.06
    criptive
    -0.06
    ="""
    -0.06
    -0.06
     iliş
    -0.06
    erah
    -0.06
    POSITIVE LOGITS
     والت
    0.07
     ア
    0.06
    .dm
    0.06
    كية
    0.06
     CONTRACT
    0.06
     declarations
    0.06
     Cond
    0.06
    인트
    0.06
     outright
    0.06
     GK
    0.06
    Activations Density 0.026%

    No Known Activations