© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 71825
    Prev
    Next
    INDEX
    Explanations

    violence and death

    np_max-act · gemini-2.0-flash

    mentions of lethal violence or calls for someone to be killed, often in political or hate-speech contexts.

    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
     DF
    -0.06
     Kardash
    -0.06
    /dialog
    -0.06
    -content
    -0.06
    (path
    -0.06
     Physicians
    -0.06
    окон
    -0.06
     Wii
    -0.06
     Islamist
    -0.06
     vengeance
    -0.06
    POSITIVE LOGITS
     cí
    0.07
     Щ
    0.07
     hukuk
    0.06
    =<
    0.06
    ři
    0.06
     mực
    0.06
    //
↵
↵
    0.06
     OpenSSL
    0.06
    sah
    0.06
    ulating
    0.06
    Activations Density 0.279%

    No Known Activations