© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 52737
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash

    mentions of trustees or trustee-related legal roles in court and bankruptcy 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
    xDA
    -0.07
     inputs
    -0.07
     BOTH
    -0.07
    Kansas
    -0.06
    .TabIndex
    -0.06
    .........
    -0.06
    628
    -0.06
     вывод
    -0.06
     Indians
    -0.06
     Pays
    -0.06
    POSITIVE LOGITS
    Importer
    0.07
     Mortgage
    0.07
    porter
    0.06
    /us
    0.06
    농
    0.06
     decreasing
    0.06
    _decl
    0.06
    Firstname
    0.06
     even
    0.06
     تط
    0.06
    Activations Density 0.032%

    No Known Activations