© 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. 99037
    Prev
    Next
    INDEX
    Explanations

    Court

    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
    ″N
    -0.08
     Trustees
    -0.07
    /entity
    -0.07
    	of
    -0.07
     columns
    -0.07
    _frag
    -0.07
     Made
    -0.07
    wer
    -0.07
    _ROOT
    -0.07
     Devices
    -0.06
    POSITIVE LOGITS
    .keyCode
    0.06
                   
    ↵
    0.06
     �
    0.06
     advisor
    0.06
     pH
    0.06
     medication
    0.06
    _td
    0.06
    강
    0.06
    xBF
    0.06
     sprinkle
    0.06
    Activations Density 0.002%

    No Known Activations