© 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. 44746
    Prev
    Next
    INDEX
    Explanations

    pain and symptoms

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of treatment response—especially the word “help” (and “did not help”) indicating whether an intervention was effective.

    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
     nasal
    -0.07
    уется
    -0.07
    ینه
    -0.06
     Ethi
    -0.06
    Detect
    -0.06
    ("[%
    -0.06
     projectiles
    -0.06
    Peter
    -0.06
     lyn
    -0.06
    Publish
    -0.06
    POSITIVE LOGITS
    portion
    0.07
    зм
    0.06
    .config
    0.06
     grub
    0.06
    .mybatis
    0.06
     Contemporary
    0.06
    户
    0.06
    GAN
    0.06
    attendance
    0.06
    904
    0.06
    Activations Density 0.015%

    No Known Activations