© 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. 11-RESID-POST-AA
    11. 55776
    Prev
    Next
    INDEX
    Explanations

    Death/Accidents

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions of someone’s death event – i.e. the actions, circumstances, or activities surrounding a person dying.

    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
     Lehr
    -0.07
     और
    -0.07
    acen
    -0.07
     Dra
    -0.06
     ERA
    -0.06
     aide
    -0.06
     Boost
    -0.06
     collapse
    -0.06
    prising
    -0.06
    ince
    -0.06
    POSITIVE LOGITS
    ‌هاي
    0.07
     国家
    0.07
     státní
    0.06
    lickr
    0.06
     vari
    0.06
     lịch
    0.06
    /oauth
    0.06
    овий
    0.06
     destined
    0.06
    闪
    0.06
    Activations Density 0.058%

    No Known Activations