© 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. 7-RESID-POST-AA
    11. 115585
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of sworn statements (affidavits/declarations) or references to supporting sworn evidence in legal documents.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ihr
    -0.08
    ()});↵
    -0.08
    _y
    -0.07
    压
    -0.07
    })↵
    -0.07
    مه
    -0.07
     negotiations
    -0.07
     قص
    -0.07
     prostitute
    -0.07
    _obj
    -0.06
    POSITIVE LOGITS
    349
    0.06
    yper
    0.06
    OTTOM
    0.06
    아
    0.06
    utut
    0.06
     CENTER
    0.06
    .Groups
    0.05
     عقد
    0.05
     bogus
    0.05
    :UIButtonTypeCustom
    0.05
    Activations Density 0.004%

    No Known Activations