© 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. 5846
    Prev
    Next
    INDEX
    Explanations

    services

    np_max-act · gemini-2.0-flash

    The neuron fires on references to professional‐services or consulting contexts, such as mentions of “consulting,” “services,” “firm,” and related industry terms.

    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
    erif
    -0.07
     domina
    -0.07
     implement
    -0.06
     دخ
    -0.06
    _sign
    -0.06
    .visit
    -0.06
     Mast
    -0.06
     gradients
    -0.06
    Е
    -0.06
    ily
    -0.06
    POSITIVE LOGITS
     куст
    0.07
    Uploader
    0.06
    $k
    0.06
    .debugLine
    0.06
    经验
    0.06
     NYT
    0.06
    ombies
    0.06
    others
    0.06
    :"
    0.06
     Advantage
    0.06
    Activations Density 0.035%

    No Known Activations