© 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. 59017
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash

    This neuron detects and highlights numerical expressions—especially floating-point numbers and other numeric values—in the text.

    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
    ｭ
    -0.07
    ţ
    -0.06
     Weston
    -0.06
     IAM
    -0.06
    ashtra
    -0.06
     Shark
    -0.06
    Justin
    -0.06
    isto
    -0.06
    _INSTALL
    -0.06
     hầu
    -0.06
    POSITIVE LOGITS
     activities
    0.07
     )
    0.07
    (IC
    0.07
     requirements
    0.07
     disposition
    0.06
     capacity
    0.06
     insufficient
    0.06
    requirements
    0.06
    にな
    0.06
     "),
    0.06
    Activations Density 0.013%

    No Known Activations