© 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
    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. 48567
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    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
    -prefix
    -0.06
    =}
    -0.06
     정부
    -0.06
     ]↵↵↵
    -0.06
    (Mat
    -0.06
    _pod
    -0.06
    >"+↵
    -0.06
    ίες
    -0.06
    amilies
    -0.06
    folk
    -0.06
    POSITIVE LOGITS
     Wealth
    0.07
    copy
    0.07
    ened
    0.07
     toilet
    0.06
     。
    0.06
     Mell
    0.06
    rie
    0.06
    oted
    0.06
     Connecticut
    0.06
     대해
    0.06
    Activations Density 0.010%

    No Known Activations