© 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. 115057
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    tokens that mark speakers, bylines, or interview/attribution labels (Q/A initials, speaker names and similar markers).

    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
    Nos
    -0.07
    laughter
    -0.07
    Boost
    -0.06
     Gors
    -0.06
    ceans
    -0.06
     battery
    -0.06
     Breast
    -0.06
    Volumes
    -0.06
    itz
    -0.06
    Exp
    -0.05
    POSITIVE LOGITS
     темп
    0.07
     Raf
    0.07
     vyvol
    0.07
     속
    0.06
     Rafael
    0.06
     sap
    0.06
     convertView
    0.06
     Sasha
    0.06
    ตาม
    0.06
     dipped
    0.06
    Activations Density 0.038%

    No Known Activations