© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89597
    Prev
    Next
    INDEX
    Explanations

    drawn-out pronunciations

    np_max-act · gemini-2.0-flash

    It detects elongated, expressive interjections or drawn‐out stretches of letters (like “Ahhh,” “Fuuuuu,” “verrrryyyy,” etc.) meant for emphasis.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [&](
    -0.06
     inds
    -0.06
     local
    -0.06
     advoc
    -0.06
     Channels
    -0.06
     pog
    -0.06
    Moh
    -0.06
     Aren
    -0.06
     Never
    -0.06
     CIS
    -0.06
    POSITIVE LOGITS
    hh
    0.07
    eeee
    0.07
    lical
    0.07
    ίδα
    0.07
    _ttl
    0.07
    hoa
    0.07
    .addListener
    0.07
    paced
    0.07
    phin
    0.07
    structural
    0.06
    Activations Density 0.010%

    No Known Activations