© 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. 59081
    Prev
    Next
    INDEX
    Explanations

    mailing list

    np_max-act · gemini-2.0-flash

    The neuron fires on mailing‐list–related header/footer tokens—e.g. “-list,” “list-admin,” “mailing list,” unsubscribe addresses, etc.

    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
     قرارداد
    -0.07
    OS
    -0.06
     scrambled
    -0.06
    meden
    -0.06
    cole
    -0.06
    .;↵
    -0.06
     деле
    -0.06
    _ACCESS
    -0.06
     slept
    -0.06
     Lena
    -0.06
    POSITIVE LOGITS
     hrom
    0.07
     Ý
    0.07
    （笑
    0.07
    虫
    0.06
     shimmer
    0.06
     dib
    0.06
     Blogger
    0.06
    JOR
    0.06
    ])*
    0.06
     arsch
    0.06
    Activations Density 0.007%

    No Known Activations