© 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. 19-RESID-POST-AA
    6. 58381
    Prev
    Next
    INDEX
    Explanations

    pottery

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _IB
    -0.06
    Plans
    -0.06
     통해
    -0.06
    .Language
    -0.06
    erging
    -0.06
    ILITY
    -0.06
     blk
    -0.06
    16
    -0.06
     rat
    -0.06
    Bel
    -0.06
    POSITIVE LOGITS
     večer
    0.06
    idos
    0.06
    MAP
    0.06
    '''↵
    0.06
     POD
    0.06
     lids
    0.06
     Troy
    0.06
     ю
    0.06
     digestion
    0.06
     д
    0.06
    Activations Density 0.019%

    No Known Activations