© 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. 68929
    Prev
    Next
    INDEX
    Explanations

    Cannes

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of film festivals and their competition or screening sections (e.g., “Cannes Film Festival,” “Un Certain Regard,” “Official Competition”).

    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
     realization
    -0.07
     fried
    -0.07
    INGS
    -0.06
     bumped
    -0.06
    Cars
    -0.06
     cooking
    -0.06
     pb
    -0.06
    iyoruz
    -0.06
     rims
    -0.06
    éis
    -0.05
    POSITIVE LOGITS
    .Fetch
    0.07
    UniformLocation
    0.07
     yanıt
    0.06
    .SetText
    0.06
    _SESSION
    0.06
    imageUrl
    0.06
    _neurons
    0.06
     Sapphire
    0.06
    ADB
    0.06
    ADX
    0.06
    Activations Density 0.003%

    No Known Activations