© 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. 7476
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on the special “<|start_header_id|>” token, i.e. it detects the start of a header‐ID tag in the text.

    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
     Colon
    -0.07
    *)
    -0.06
    таки
    -0.06
    makes
    -0.06
    -vous
    -0.06
    cols
    -0.06
    anas
    -0.06
    _MENU
    -0.06
    ders
    -0.06
     firmware
    -0.06
    POSITIVE LOGITS
     уточ
    0.06
     ủy
    0.06
    shaft
    0.06
     Morocco
    0.06
    chied
    0.06
     quotation
    0.06
     лицо
    0.06
    usat
    0.06
     Raqqa
    0.05
     Politico
    0.05
    Activations Density 0.004%

    No Known Activations