© 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. 19-RESID-POST-AA
    11. 124895
    Prev
    Next
    INDEX
    Explanations

    start

    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
    _dict
    -0.07
    (bin
    -0.07
     bez
    -0.06
     HttpClientModule
    -0.06
    -bed
    -0.06
     Purch
    -0.06
     bins
    -0.06
     checkboxes
    -0.06
     hovered
    -0.06
     Clin
    -0.06
    POSITIVE LOGITS
     start
    0.14
    start
    0.14
     starts
    0.12
     Start
    0.11
    Start
    0.11
     started
    0.10
     starting
    0.09
     Started
    0.09
    Started
    0.09
    程
    0.09
    Activations Density 0.090%

    No Known Activations