© 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 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. 7-RESID-POST-AA
    11. 28978
    Prev
    Next
    INDEX
    Explanations

    Assistant

    np_max-act · gemini-2.0-flash

    It detects tokens belonging to assistant responses (the "assistant" role / assistant-generated segments).

    oai_token-act-pair · gpt-5-miniTriggered 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
    =\"$
    -0.07
    лим
    -0.07
    .gb
    -0.06
     colour
    -0.06
    Fatal
    -0.06
     Relatives
    -0.06
    Around
    -0.06
    โลย
    -0.06
     تصميم
    -0.06
    Redux
    -0.06
    POSITIVE LOGITS
     ROLE
    0.07
     sway
    0.06
     listening
    0.06
    TestData
    0.06
    poll
    0.06
    θα
    0.06
     SETUP
    0.06
    scheduler
    0.06
    -bodied
    0.06
    cpt
    0.06
    Activations Density 0.140%

    No Known Activations