© 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. 23-RESID-POST-AA
    11. 66339
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turf
    -0.07
     mehr
    -0.06
    itten
    -0.06
    >
↵
↵
↵
    -0.06
     medically
    -0.06
     }↵↵↵↵
    -0.06
    ActionTypes
    -0.06
     Mondays
    -0.06
    ΟΥ
    -0.06
     ninja
    -0.06
    POSITIVE LOGITS
    Clients
    0.07
     taraf
    0.07
     proporcion
    0.07
    	state
    0.07
    影响
    0.06
    に関する
    0.06
    ccess
    0.06
     joins
    0.06
    !).
    0.06
    ตรง
    0.06
    Activations Density 5.461%

    No Known Activations