© 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 EvalsExportsAPI 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. 38114
    Prev
    Next
    INDEX
    Explanations

    198

    np_max-act · gemini-2.0-flash

    legal terms related to civil rights and prison conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects citations of the federal civil-rights statute “42 U.S.C. § 1983.”

    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
    Dub
    -0.06
     progressDialog
    -0.06
     dub
    -0.06
     summaries
    -0.06
     forCell
    -0.06
    .swt
    -0.06
    욱
    -0.06
    _BU
    -0.06
    uat
    -0.06
    -On
    -0.06
    POSITIVE LOGITS
    acies
    0.07
     declines
    0.07
     Diary
    0.07
     이후
    0.07
    -blood
    0.07
    _trade
    0.07
    ,start
    0.06
     Towards
    0.06
     Regression
    0.06
    _after
    0.06
    Activations Density 0.001%

    No Known Activations