© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109280
    Prev
    Next
    INDEX
    Explanations

    Film and cameras

    np_max-act · gemini-2.0-flash

    This neuron activates on phrases describing technical filmmaking and cinematography—especially mentions of camera movement, angles, and how scenes look on screen.

    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
    hunt
    -0.07
    Callable
    -0.07
    应当
    -0.06
     nejvyšší
    -0.06
    かな
    -0.06
    nah
    -0.06
     хочу
    -0.06
    真的
    -0.06
     newborn
    -0.06
     tylko
    -0.06
    POSITIVE LOGITS
     ALTER
    0.07
    icipant
    0.07
     чай
    0.07
     [
    0.07
     Registers
    0.06
     Proposition
    0.06
     racing
    0.06
    >[
    0.06
     delic
    0.06
    onder
    0.06
    Activations Density 0.019%

    No Known Activations