© 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. 7-RESID-POST-AA
    11. 43677
    Prev
    Next
    INDEX
    Explanations

    ics/etics endings

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /domain
    -0.07
     cube
    -0.07
     shown
    -0.07
     le
    -0.07
     scalable
    -0.07
     Le
    -0.06
    566
    -0.06
    send
    -0.06
     send
    -0.06
     appl
    -0.06
    POSITIVE LOGITS
     genetics
    0.11
    ics
    0.11
     physics
    0.10
    ICS
    0.10
    physics
    0.10
    odynamics
    0.09
     dynamics
    0.09
    istics
    0.09
     robotics
    0.09
    hetics
    0.09
    Activations Density 0.049%

    No Known Activations