© 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. 7134
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on section headings and structural labels (e.g., “sec,” section numbers, “### Crystal data,” etc.).

    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
    perial
    -0.07
    _ring
    -0.06
     ฟร
    -0.06
    >t
    -0.06
    _theta
    -0.06
     separates
    -0.06
    输
    -0.06
    zeigt
    -0.06
    ｧ
    -0.06
    *cos
    -0.06
    POSITIVE LOGITS
     notions
    0.07
    .setResult
    0.07
     skilled
    0.07
     fees
    0.06
    ’s
    0.06
     Windsor
    0.06
     dialog
    0.06
     banka
    0.06
    _sql
    0.06
     Raj
    0.06
    Activations Density 0.001%

    No Known Activations