© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38389
    Prev
    Next
    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it does not respond to any tokens.

    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
    leck
    -0.07
    Avoid
    -0.06
    Managed
    -0.06
    _adapter
    -0.06
     手
    -0.06
    <Rigidbody
    -0.06
     ''){↵
    -0.06
    Ult
    -0.06
    :c
    -0.06
    **/↵
    -0.05
    POSITIVE LOGITS
    _proj
    0.07
     klass
    0.07
    ARED
    0.07
     Holdings
    0.06
     per
    0.06
     lest
    0.06
    ียว
    0.06
     Ball
    0.06
     Spears
    0.06
    _value
    0.06
    Activations Density 0.012%

    No Known Activations