© 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. 63374
    Prev
    Next
    INDEX
    Explanations

    named

    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
    halt
    -0.07
    زارش
    -0.07
    -wage
    -0.07
     Seconds
    -0.06
    (tbl
    -0.06
     '((
    -0.06
     densities
    -0.06
     vám
    -0.06
    _DRIVE
    -0.06
     Particip
    -0.06
    POSITIVE LOGITS
    TEX
    0.06
    mah
    0.06
     खड
    0.06
    ;]/
    0.06
    wrapper
    0.06
    “The
    0.06
    “For
    0.06
    /top
    0.06
    under
    0.06
     สามารถ
    0.06
    Activations Density 0.041%

    No Known Activations