© 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. 11-RESID-POST-AA
    11. 47235
    Prev
    Next
    INDEX
    Explanations

    <

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ubuntu
    -0.07
     キ
    -0.07
     müzik
    -0.07
    itary
    -0.07
    .slot
    -0.06
    果
    -0.06
    =message
    -0.06
     Kadın
    -0.06
    _smart
    -0.06
     syscall
    -0.06
    POSITIVE LOGITS
    ？
    0.06
     Rear
    0.06
    .Full
    0.06
     flowers
    0.06
     Riverside
    0.06
     Papers
    0.06
    Pre
    0.06
    chef
    0.06
     Labor
    0.06
    cannot
    0.06
    Activations Density 0.020%

    No Known Activations