© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126745
    Prev
    Next
    INDEX
    Explanations

    vent

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of ventilation or airflow–related safety measures (e.g., “ventilated,” “air,” “respirator”) indicating it’s looking for references to proper ventilation or respiratory protection.

    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
     particles
    -0.06
     shards
    -0.06
     loaders
    -0.06
     đỡ
    -0.06
    IsEmpty
    -0.06
    ToJson
    -0.06
    undaki
    -0.06
     경기
    -0.06
    '])
    -0.05
     Celt
    -0.05
    POSITIVE LOGITS
     nově
    0.07
    rej
    0.07
    фров
    0.06
     рез
    0.06
    �
    0.06
    >x
    0.06
     workout
    0.06
     bj
    0.06
     markup
    0.06
    coordinates
    0.06
    Activations Density 0.002%

    No Known Activations