© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 44111
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    structured, non-prose metadata such as headers, lists, measurements, IDs, contact details, and other formatted fields in documents.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лаж
    -0.07
    /mat
    -0.06
     mounts
    -0.06
    /utils
    -0.06
    _SAMPLES
    -0.06
    868
    -0.06
    jist
    -0.06
    .ObjectModel
    -0.06
    猫
    -0.06
    268
    -0.06
    POSITIVE LOGITS
    :↵
    0.09
    　↵
    0.08
    ↵
    0.08
    ,"↵
    0.07
    ’↵
    0.07
          ↵
    0.07
    )↵
    0.07
         ↵
    0.07
     ↵
    0.07
    (){↵
    0.07
    Activations Density 0.104%

    No Known Activations