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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90712
    Prev
    Next
    INDEX
    Explanations

    hands

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions of placing hands on a body or object (e.g. “hands on hips,” “hands on either side,” etc.).

    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
     piyas
    -0.07
     newVal
    -0.07
     ринку
    -0.06
     Sep
    -0.06
     PLUGIN
    -0.06
     perfect
    -0.06
    (actor
    -0.06
    ۲۸
    -0.06
    ('='
    -0.06
     东
    -0.06
    POSITIVE LOGITS
     stations
    0.07
     epilepsy
    0.06
     Hands
    0.06
    ausal
    0.06
    最初
    0.06
    _CYCLE
    0.06
     hands
    0.06
    -run
    0.06
     Tu
    0.06
     touches
    0.06
    Activations Density 0.013%

    No Known Activations