© 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. 33987
    Prev
    Next
    INDEX
    Explanations

    iddle

    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
     capability
    -0.07
    pv
    -0.06
    (nums
    -0.06
    ávis
    -0.06
    фор
    -0.06
     capabilities
    -0.06
    uru
    -0.06
     Burns
    -0.06
    มหานคร
    -0.06
    írk
    -0.06
    POSITIVE LOGITS
    üyle
    0.07
     нее
    0.07
    줄
    0.07
     besteht
    0.07
     празд
    0.07
     Dental
    0.07
    full
    0.06
     حض
    0.06
     Pied
    0.06
    pled
    0.06
    Activations Density 0.002%

    No Known Activations