© 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. 57574
    Prev
    Next
    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the occurrence of the word “language,” especially in license‐header phrases.

    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
    Æ
    -0.07
     Sr
    -0.07
     στο
    -0.07
    Red
    -0.07
    門
    -0.06
     tane
    -0.06
    -black
    -0.06
    ,False
    -0.06
     都
    -0.06
    ({
    -0.06
    POSITIVE LOGITS
     سخن
    0.09
     المنت
    0.07
     heure
    0.07
     annex
    0.07
    LU
    0.06
     />,
    0.06
     ویژه
    0.06
     newcom
    0.06
     Created
    0.06
    Https
    0.06
    Activations Density 0.001%

    No Known Activations