© 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. 44435
    Prev
    Next
    INDEX
    Explanations

    Outdoor locations

    np_max-act · gemini-2.0-flash

    The neuron fires on words that describe active, movement‐oriented outdoor activities (e.g. “go,” “hike,” “outside,” “visiting”).

    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
     matrices
    -0.07
    -follow
    -0.07
     wonder
    -0.07
    its
    -0.07
    *q
    -0.07
     gameObject
    -0.07
    mamız
    -0.06
     leveling
    -0.06
    .include
    -0.06
     negatively
    -0.06
    POSITIVE LOGITS
    give
    0.06
     clap
    0.06
     cleans
    0.06
    (";
    0.06
     střední
    0.06
     아
    0.06
    heard
    0.06
    tain
    0.05
    wins
    0.05
    (gui
    0.05
    Activations Density 0.057%

    No Known Activations