© 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. 114954
    Prev
    Next
    INDEX
    Explanations

    medical and scientific texts

    np_max-act · gemini-2.0-flash

    hyphenated and acronym/abbreviation-heavy technical phrases—especially split morphemes and punctuation typical of scientific or medical writing.

    oai_token-act-pair · gpt-5Triggered 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
    ยม
    -0.07
     Lean
    -0.07
     cron
    -0.07
     eux
    -0.06
    مارات
    -0.06
    SSERT
    -0.06
    عر
    -0.06
     CHR
    -0.06
     leider
    -0.06
    憶
    -0.06
    POSITIVE LOGITS
     ARISING
    0.07
    .Group
    0.06
    emphasis
    0.06
    .thumb
    0.06
    ]},↵
    0.06
    ่า
    0.06
    =[]↵
    0.06
     Whatsapp
    0.06
    Wildcard
    0.06
    configuration
    0.06
    Activations Density 1.416%

    No Known Activations