© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27-RESID-POST-AA
    11. 7178
    Prev
    Next
    INDEX
    Explanations

    cell/cells

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .restart
    -0.07
     descri
    -0.07
    voor
    -0.07
    .spinner
    -0.07
    43
    -0.07
    209
    -0.06
    ought
    -0.06
    RYPT
    -0.06
     Juni
    -0.06
    ania
    -0.06
    POSITIVE LOGITS
    Cell
    0.10
     cellular
    0.10
     cell
    0.10
     Cell
    0.09
    -cell
    0.09
     cells
    0.09
     CELL
    0.08
    acellular
    0.08
     Cells
    0.08
    atient
    0.07
    Activations Density 0.064%

    No Known Activations