© 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. 35268
    Prev
    Next
    INDEX
    Explanations

    pressure

    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
    保護
    -0.07
    |↵↵
    -0.06
    规定
    -0.06
    igh
    -0.06
     ری
    -0.06
    면
    -0.06
     直
    -0.06
    間
    -0.06
    损
    -0.06
    �장
    -0.06
    POSITIVE LOGITS
    param
    0.08
     AMC
    0.07
     Moments
    0.07
    (grad
    0.06
    spec
    0.06
    chandle
    0.06
     PropertyChanged
    0.06
     Fritz
    0.06
    .Native
    0.06
     push
    0.06
    Activations Density 0.007%

    No Known Activations