© 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. 30833
    Prev
    Next
    INDEX
    Explanations

    suggest

    np_max-act · gemini-2.0-flash

    This neuron detects when the text is offering advice or recommendations, i.e. verbs like “propose” and “suggest.”

    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
     chassis
    -0.07
     sayf
    -0.07
    uniacid
    -0.06
     cylinders
    -0.06
     partes
    -0.06
    ogeneous
    -0.06
     Contrast
    -0.06
     signs
    -0.06
     tostring
    -0.06
    =s
    -0.06
    POSITIVE LOGITS
     suggesting
    0.08
     suggested
    0.07
    Œ
    0.07
     suggest
    0.07
     proposing
    0.07
    HASH
    0.07
    imos
    0.07
     recommend
    0.07
    ıyoruz
    0.06
    ~~~~
    0.06
    Activations Density 0.023%

    No Known Activations