© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39144
    Prev
    Next
    INDEX
    Explanations

    combining

    np_max-act · gemini-2.0-flash

    The neuron fires on the special control‐ and metadata‐marker tokens (e.g. <|begin_of_text|>, header IDs, system/user tags) rather than on ordinary content words.

    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
    WhatsApp
    -0.07
    낸
    -0.06
    34
    -0.06
    iniz
    -0.06
    ONE
    -0.06
    xbd
    -0.06
    く
    -0.06
    _USB
    -0.06
     Rotary
    -0.06
     Carp
    -0.06
    POSITIVE LOGITS
     coords
    0.07
     secular
    0.07
    (background
    0.07
     فض
    0.07
     expos
    0.07
    λία
    0.06
    Translations
    0.06
    очного
    0.06
     destabil
    0.06
    featured
    0.06
    Activations Density 0.036%

    No Known Activations