© 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. 11-RESID-POST-AA
    11. 19041
    Prev
    Next
    INDEX
    Explanations

    Duplicates

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suicide
    -0.06
    journal
    -0.06
     secretly
    -0.06
    /DTD
    -0.06
    _Save
    -0.06
    escape
    -0.06
    Fu
    -0.06
     Jihad
    -0.06
    'utilisation
    -0.06
    ません
    -0.06
    POSITIVE LOGITS
     middle
    0.06
     substr
    0.06
     CONTENT
    0.06
    .sql
    0.06
    (child
    0.06
     중
    0.06
     अस
    0.06
     robbed
    0.06
    (mm
    0.06
     osób
    0.06
    Activations Density 0.023%

    No Known Activations