© 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. 57685
    Prev
    Next
    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash

    The neuron fires on terms related to installing software dependencies (e.g. “install,” “packages,” “dependencies,” “pip,” “requirements”).

    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
    ukan
    -0.06
    Thunk
    -0.06
     никогда
    -0.06
    .ObjectMapper
    -0.06
    ImplOptions
    -0.06
    AndServe
    -0.06
     QPixmap
    -0.06
    785
    -0.06
    demand
    -0.06
     Cost
    -0.06
    POSITIVE LOGITS
    ?“
    0.07
    !'
    0.07
     Bye
    0.07
    centration
    0.07
     �
    0.06
     vaccination
    0.06
    égor
    0.06
    ?'
    0.06
    _COMPONENT
    0.06
     xx
    0.06
    Activations Density 0.012%

    No Known Activations