© 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. 70708
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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
     historia
    -0.06
     Однако
    -0.06
     teamed
    -0.06
    ��
    -0.06
    edited
    -0.06
     Testament
    -0.06
    unlikely
    -0.06
    Wire
    -0.06
     Geschichte
    -0.06
    альных
    -0.06
    POSITIVE LOGITS
    \
    ↵
    0.08
    paginate
    0.07
     Holt
    0.07
     phoenix
    0.07
    Bitcoin
    0.06
    979
    0.06
     grp
    0.06
    _APB
    0.06
    Ц
    0.06
     ч
    0.06
    Activations Density 0.000%

    No Known Activations