© 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. 126845
    Prev
    Next
    INDEX
    Explanations

    core muscles

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of core-stability and balance exercises—especially those involving a fitness (stability) ball.

    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
    uish
    -0.07
    <Result
    -0.07
     Sport
    -0.06
     Turk
    -0.06
     Vienna
    -0.06
     nổi
    -0.06
     Viet
    -0.06
     stress
    -0.06
     bidding
    -0.06
    _CONNECT
    -0.06
    POSITIVE LOGITS
    ΡΓ
    0.07
    走
    0.06
     IMO
    0.06
    ्ष
    0.06
    _tot
    0.06
    .schedulers
    0.06
    razione
    0.06
    lg
    0.06
    spir
    0.06
    (PDO
    0.06
    Activations Density 0.004%

    No Known Activations