© 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 EvalsExportsAPI 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. 6663
    Prev
    Next
    INDEX
    Explanations

    acceptability or allowance

    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
    сте
    -0.07
     ऊ
    -0.06
     Pap
    -0.06
    tega
    -0.06
    Console
    -0.06
    ificados
    -0.06
     denomin
    -0.06
     Slate
    -0.06
    .union
    -0.06
     complementary
    -0.06
    POSITIVE LOGITS
     grin
    0.07
     Slovakia
    0.06
    '|
    0.06
     UIViewController
    0.06
    android
    0.06
    hin
    0.06
    ernaut
    0.06
    ельзя
    0.06
    lerinin
    0.06
     ait
    0.06
    Activations Density 0.048%

    No Known Activations