© 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
    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. 98295
    Prev
    Next
    INDEX
    Explanations

    possible infection, diagnosis

    np_max-act · gemini-2.0-flash

    words that mark diagnostic status or uncertainty (e.g., possible, suspected, confirmed, diagnosis).

    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
     splice
    -0.06
    ж
    -0.06
    _department
    -0.06
    票
    -0.06
    Ear
    -0.06
    bk
    -0.06
    TEXT
    -0.06
    -inst
    -0.06
     \"
    -0.06
    specialchars
    -0.06
    POSITIVE LOGITS
     کارگرد
    0.08
     Terrace
    0.06
     thiếu
    0.06
    .messages
    0.06
     xr
    0.06
     pH
    0.06
     statically
    0.06
    .Interfaces
    0.06
    seeing
    0.06
    .Sub
    0.06
    Activations Density 0.214%

    No Known Activations