© 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. 110714
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the cost or fees of a food permit (especially phrases like “the cost in Florida”).

    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
    TOCOL
    -0.06
     Persistent
    -0.06
     gsi
    -0.06
    the
    -0.06
     fuzzy
    -0.06
     열
    -0.06
    갑
    -0.06
     Gems
    -0.06
     descendants
    -0.06
     occurrence
    -0.06
    POSITIVE LOGITS
     dataSize
    0.07
     GetValue
    0.06
    kr
    0.06
     speakers
    0.06
    ;",↵
    0.06
    .ColumnHeader
    0.06
    (frame
    0.06
    .WEST
    0.06
    capital
    0.06
     erot
    0.06
    Activations Density 0.081%

    No Known Activations