© 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. 56093
    Prev
    Next
    INDEX
    Explanations

    scientific words

    np_max-act · gemini-2.0-flash

    terms related to antibodies and their production methods.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of concrete material or substrate terms (e.g. “clay,” “shelving,” “ware”).

    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
     anyhow
    -0.07
     jelly
    -0.07
     Petit
    -0.06
     تض
    -0.06
    Directed
    -0.06
     gem
    -0.06
     Shipping
    -0.06
    ifornia
    -0.06
    ov
    -0.06
    _dialog
    -0.06
    POSITIVE LOGITS
     ActiveRecord
    0.07
    /"+
    0.06
     профилакти
    0.06
     と
    0.06
     отвер
    0.06
     motivo
    0.06
    】,【
    0.06
     EOF
    0.06
    ResultsController
    0.06
    _CTL
    0.06
    Activations Density 0.049%

    No Known Activations