© 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. 41373
    Prev
    Next
    INDEX
    Explanations

    worry

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on mentions of anxiety‐related terms (e.g., “anxiety,” “panic attacks”).

    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
    \Mapping
    -0.06
    ensed
    -0.06
    碰
    -0.06
     reinforced
    -0.06
    vised
    -0.06
    iances
    -0.06
    *******
↵
    -0.06
     anthem
    -0.06
    _mesh
    -0.06
    faces
    -0.06
    POSITIVE LOGITS
     BEEN
    0.07
     pea
    0.07
     близ
    0.06
    -sub
    0.06
     остав
    0.06
     thorough
    0.06
     eksik
    0.06
     Ryan
    0.06
     чи
    0.06
     lista
    0.06
    Activations Density 0.011%

    No Known Activations