© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RESID-POST-AA
    11. 48014
    Prev
    Next
    INDEX
    Explanations

    lists of features/options

    np_max-act · gemini-2.0-flash

    phrases and tokens that introduce explanations or lists (e.g., "there are several", "reasons", "include", numbered list markers).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    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
    Negative Logits
     Tun
    -0.07
     Mansion
    -0.07
    왕
    -0.07
     Var
    -0.06
     commenc
    -0.06
     temple
    -0.06
    _func
    -0.06
    _minimum
    -0.06
     Nigeria
    -0.06
    Building
    -0.06
    POSITIVE LOGITS
     "@
    0.07
    =""></
    0.07
     gratuiti
    0.06
    %',↵
    0.06
     ********************************************************************************
    0.06
    적인
    0.06
    ΙΔ
    0.06
    @mail
    0.06
    大き
    0.06
     StringType
    0.06
    Activations Density 0.383%

    No Known Activations