© 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. 80325
    Prev
    Next
    INDEX
    Explanations

    align

    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
    菜
    -0.07
     коллек
    -0.06
     SME
    -0.06
     해당
    -0.06
     quelques
    -0.06
     cuent
    -0.06
     findOne
    -0.06
    ,color
    -0.06
    .Acc
    -0.06
    <Sprite
    -0.06
    POSITIVE LOGITS
     Episodes
    0.06
    Highlights
    0.06
    otionEvent
    0.06
    !="
    0.06
     resolved
    0.06
    	pass
    0.06
     losses
    0.06
    acellular
    0.06
    dsn
    0.06
     keyst
    0.06
    Activations Density 0.004%

    No Known Activations