© 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. 28001
    Prev
    Next
    INDEX
    Explanations

    devastating

    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
     Ear
    -0.07
    .Mod
    -0.07
    Old
    -0.06
    	method
    -0.06
     improper
    -0.06
    ool
    -0.06
     Old
    -0.06
     Lent
    -0.06
     ear
    -0.06
     prayer
    -0.06
    POSITIVE LOGITS
     devastated
    0.11
     devastating
    0.11
     devast
    0.10
     devastation
    0.09
     evacuate
    0.08
     catast
    0.08
    -ev
    0.07
    ุธ
    0.07
    adí
    0.07
    vin
    0.07
    Activations Density 0.004%

    No Known Activations