© 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. 54526
    Prev
    Next
    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on mentions of “process,” marking references to procedural or step‐by‐step descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    the production processes of various chemical compounds.

    oai_token-act-pair · gpt-4o-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
     вв
    -0.06
    assador
    -0.06
    824
    -0.06
    ниці
    -0.06
    书
    -0.06
     servicio
    -0.06
    (div
    -0.06
    اطعة
    -0.06
     teş
    -0.06
     scissors
    -0.06
    POSITIVE LOGITS
    gener
    0.07
    ASI
    0.06
     adjusting
    0.06
    Ả
    0.06
    .Program
    0.06
    Anna
    0.06
    _fifo
    0.06
    Simply
    0.06
     말을
    0.06
     bolts
    0.06
    Activations Density 0.008%

    No Known Activations