© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 37337
    Prev
    Next
    INDEX
    Explanations

    sudden changes/difficulties

    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
     Madd
    -0.07
     mon
    -0.07
    jit
    -0.06
    DDevice
    -0.06
     DAN
    -0.06
     Cowboys
    -0.06
    ělí
    -0.06
    political
    -0.06
     Sunset
    -0.06
    انگ
    -0.06
    POSITIVE LOGITS
     cram
    0.06
     attributable
    0.06
    του
    0.06
     الآ
    0.06
     batting
    0.05
     meydana
    0.05
     disciplinary
    0.05
     ö
    0.05
     accountant
    0.05
    RI
    0.05
    Activations Density 0.000%

    No Known Activations