© 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. 23087
    Prev
    Next
    INDEX
    Explanations

    bombs

    np_max-act · gemini-2.0-flash

    references to nuclear weapons and their disarmament in hypothetical scenarios.

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

    The neuron fires on vocabulary about bombs and their disarmament—words like “bomb,” “timer,” “warhead,” and “disarm.”

    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
    PDF
    -0.07
     Money
    -0.06
     Graphic
    -0.06
     weld
    -0.06
    .valid
    -0.06
     provide
    -0.06
    Form
    -0.06
     conversation
    -0.06
    drop
    -0.06
     basin
    -0.06
    POSITIVE LOGITS
    经
    0.07
     федераль
    0.06
     khảo
    0.06
    pellier
    0.06
    brero
    0.06
    OMET
    0.06
    �
    0.06
    ционный
    0.06
     creampie
    0.06
     letterSpacing
    0.06
    Activations Density 0.009%

    No Known Activations