© 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. 6047
    Prev
    Next
    INDEX
    Explanations

    collaboration

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of professional or collaborative skills—especially terms like “teamwork,” “project management,” and similar ability names.

    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
     hindi
    -0.07
    partial
    -0.06
    855
    -0.06
     pursuit
    -0.06
     Suite
    -0.06
     labyrinth
    -0.06
    拉
    -0.06
    563
    -0.06
     offs
    -0.05
    INT
    -0.05
    POSITIVE LOGITS
    ASI
    0.06
     contag
    0.06
    ával
    0.06
     approve
    0.06
    soles
    0.06
    .sym
    0.06
     sposób
    0.06
    ώσεις
    0.06
     Contributions
    0.06
    ilver
    0.06
    Activations Density 0.093%

    No Known Activations