© 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. 121506
    Prev
    Next
    INDEX
    Explanations

    Meta-analyses

    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
     Cs
    -0.07
     CAS
    -0.06
    Nam
    -0.06
    ossed
    -0.06
    (gt
    -0.06
     propriet
    -0.06
     aup
    -0.06
     асп
    -0.06
     domaine
    -0.06
     cin
    -0.06
    POSITIVE LOGITS
     Bernie
    0.10
     Kanye
    0.08
    _ios
    0.08
    _OCC
    0.07
    @GeneratedValue
    0.07
    PMC
    0.07
    ];//
    0.07
    ))*
    0.07
     nét
    0.07
    relude
    0.07
    Activations Density 0.002%

    No Known Activations