© 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. 58630
    Prev
    Next
    INDEX
    Explanations

    Perspective in videos

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of a camera’s “ball’s-eye view,” i.e. a camera embedded inside a ball.

    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
    -backed
    -0.07
    期间
    -0.06
    :]:↵
    -0.06
    	direction
    -0.06
     Options
    -0.06
     Cait
    -0.06
     "%
    -0.06
     =[
    -0.06
    ITE
    -0.06
     chậm
    -0.06
    POSITIVE LOGITS
     khu
    0.07
    ocyte
    0.07
    trieve
    0.06
    /form
    0.06
    _INTER
    0.06
    getField
    0.06
    anst
    0.06
    Singleton
    0.06
    lag
    0.06
    ylim
    0.06
    Activations Density 0.064%

    No Known Activations