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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1416
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by instances of the copular verb “is” (and similar “to be” forms).

    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
     gra
    -0.07
    Evaluate
    -0.07
     Transformation
    -0.06
     подроб
    -0.06
    VIEW
    -0.06
    gzip
    -0.06
     индивиду
    -0.06
     Lav
    -0.06
    Standard
    -0.06
    коном
    -0.06
    POSITIVE LOGITS
    .isEnabled
    0.06
     根
    0.06
     barren
    0.06
     втор
    0.06
     دور
    0.06
     gelen
    0.06
    className
    0.06
     �
    0.05
     vur
    0.05
    irst
    0.05
    Activations Density 0.068%

    No Known Activations