Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109967
    Prev
    Next
    INDEX
    Explanations

    cinemat

    np_max-act · gemini-2.0-flash

    The neuron fires on language describing a film’s visual and camera craft—terms about cinematography, lighting, shot design, editing, and visual style.

    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
    ि�
    -0.06
    تیب
    -0.06
     Hund
    -0.06
    _ke
    -0.06
     degli
    -0.06
    (strcmp
    -0.06
     Preis
    -0.06
    !!
    -0.06
    κτή
    -0.06
    Maintenance
    -0.06
    POSITIVE LOGITS
    .Singleton
    0.07
    rna
    0.06
     vfs
    0.06
    .CONFIG
    0.06
    colors
    0.06
     instability
    0.06
    groundColor
    0.06
    -confidence
    0.06
     cinemat
    0.06
     張
    0.06
    Activations Density 0.012%

    No Known Activations