© 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. 93549
    Prev
    Next
    INDEX
    Explanations

    Windows

    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
     پ
    -0.08
     Prefix
    -0.07
     demeanor
    -0.06
     افزار
    -0.06
    .mainloop
    -0.06
     المص
    -0.06
    _MISC
    -0.06
     อ
    -0.06
    ト
    -0.06
     aficion
    -0.06
    POSITIVE LOGITS
     Windows
    0.15
    Windows
    0.10
     JACK
    0.08
    -windows
    0.07
    _votes
    0.07
    ива
    0.07
    arest
    0.07
    stanov
    0.06
     Exchange
    0.06
     regulated
    0.06
    Activations Density 0.011%

    No Known Activations