© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129857
    Prev
    Next
    INDEX
    Explanations

    astronomy

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on astronomy- and cosmology-related terms (e.g., “astronomy,” “astronomical,” “cosmology”).

    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
     layered
    -0.09
     label
    -0.07
     LEVEL
    -0.07
     králov
    -0.07
     cellphone
    -0.07
     pozisyon
    -0.07
     CAR
    -0.07
     Marin
    -0.07
    389
    -0.07
     memcmp
    -0.07
    POSITIVE LOGITS
     Astronomy
    0.10
     Astr
    0.09
     astronomy
    0.09
     Ast
    0.09
     astronom
    0.08
     Astro
    0.08
     Aston
    0.08
     astronomers
    0.08
    Ast
    0.08
     astronomical
    0.08
    Activations Density 0.009%

    No Known Activations