© 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. 12665
    Prev
    Next
    INDEX
    Explanations

    genetic algorithms

    np_max-act · gemini-2.0-flash

    The neuron activates for terminology and function names specific to genetic algorithms (e.g., population, fitness, mutation, crossover, chromosome).

    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
     petals
    -0.07
     У
    -0.07
    _Word
    -0.06
    "W
    -0.06
     ткани
    -0.06
    ‌شد
    -0.06
    (chunk
    -0.06
    .baomidou
    -0.06
    十四
    -0.06
    У
    -0.06
    POSITIVE LOGITS
     artworks
    0.06
     empleado
    0.06
     actividades
    0.06
    ổi
    0.06
     kredi
    0.06
    proj
    0.06
    Sense
    0.06
     Bread
    0.06
    January
    0.06
    NSMutableDictionary
    0.06
    Activations Density 0.007%

    No Known Activations