© 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. 39103
    Prev
    Next
    INDEX
    Explanations

    legal rulings

    np_max-act · gemini-2.0-flash

    This neuron fires on the standard appellate‐review phrase “will not be disturbed,” marking passages that state lower-court findings will remain intact.

    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
    BindingUtil
    -0.06
     hips
    -0.06
     Balt
    -0.06
     hawk
    -0.06
     transistor
    -0.06
    markup
    -0.06
     cmd
    -0.06
     dagen
    -0.06
    Here
    -0.06
    র
    -0.06
    POSITIVE LOGITS
    čních
    0.07
    ONO
    0.07
    :maj
    0.07
    งาน
    0.07
    .lon
    0.07
     limiting
    0.06
     damn
    0.06
     Josef
    0.06
    YC
    0.06
     ・
    0.06
    Activations Density 0.005%

    No Known Activations