© 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. 128592
    Prev
    Next
    INDEX
    Explanations

    Citations in specific format

    np_max-act · gemini-2.0-flash

    The neuron activates on inline citation or reference markers (e.g., bracketed “[ @r… ]” labels).

    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
     MMI
    -0.06
    aginator
    -0.06
    .'</
    -0.06
    boot
    -0.06
     cheaper
    -0.06
     isError
    -0.06
    _ca
    -0.06
    istring
    -0.06
     worm
    -0.06
    /products
    -0.06
    POSITIVE LOGITS
     Flatten
    0.07
    -base
    0.07
    ハ
    0.06
     Famil
    0.06
    NI
    0.06
     rallying
    0.06
    .table
    0.06
     duties
    0.06
     nó
    0.06
     ناح
    0.06
    Activations Density 0.022%

    No Known Activations