© 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. 3-RESID-POST-AA
    11. 93660
    Prev
    Next
    INDEX
    Explanations

    Verb

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %p
    -0.06
     TOUR
    -0.06
    #↵
    -0.06
     trat
    -0.06
    tour
    -0.06
     Tour
    -0.06
     ],
    -0.06
     UV
    -0.06
    uplicates
    -0.06
     近
    -0.06
    POSITIVE LOGITS
    werk
    0.12
     Werk
    0.12
     werk
    0.10
     wrought
    0.10
     Verb
    0.09
     verb
    0.08
     веществ
    0.08
    Verb
    0.07
     substance
    0.07
    /database
    0.07
    Activations Density 0.005%

    No Known Activations