© 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. 110835
    Prev
    Next
    INDEX
    Explanations

    email excerpts

    np_max-act · gemini-2.0-flash

    This neuron triggers on tokens that refer to using or considering the full conversation context in instructions.

    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
    naissance
    -0.07
    ETING
    -0.06
    versed
    -0.06
    ponde
    -0.06
     fisse
    -0.06
    -health
    -0.06
    gems
    -0.06
     geldi
    -0.06
     dusty
    -0.06
    gone
    -0.06
    POSITIVE LOGITS
    _drag
    0.08
    ">';
↵
    0.07
     एस
    0.07
    Gi
    0.06
     اف
    0.06
    ồi
    0.06
     асп
    0.06
    edes
    0.06
    ротив
    0.06
    oliday
    0.06
    Activations Density 0.011%

    No Known Activations