© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8937
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash

    This neuron activates on uppercase section‐heading labels and other all‐caps tokens marking structured document sections.

    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
     videog
    -0.07
    events
    -0.07
    าสตร
    -0.07
     MSG
    -0.06
    ้าอ
    -0.06
     regrets
    -0.06
    contador
    -0.06
    山
    -0.06
     userList
    -0.06
     lect
    -0.06
    POSITIVE LOGITS
     région
    0.06
     Час
    0.06
    pectral
    0.06
    ichTextBox
    0.06
     hava
    0.06
    луата
    0.06
    Cb
    0.06
    _GB
    0.06
     comic
    0.06
    альная
    0.06
    Activations Density 0.014%

    No Known Activations