© 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. 55945
    Prev
    Next
    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash

    This neuron fires on section-heading or title tokens (e.g. “Legislativo,” “stage,” “Visual Mode”) that mark the start of a new document section.

    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
    .Part
    -0.07
     Paul
    -0.06
    .dt
    -0.06
     juxtap
    -0.06
     مساحت
    -0.06
    :
↵
↵
    -0.06
    evt
    -0.06
     Quảng
    -0.06
    291
    -0.06
    ("@
    -0.06
    POSITIVE LOGITS
    ыс
    0.06
    iser
    0.06
    еры
    0.06
    灰
    0.06
    setFlash
    0.06
     assays
    0.06
     добавить
    0.06
    portlet
    0.06
    사랑
    0.06
    Mismatch
    0.06
    Activations Density 0.100%

    No Known Activations