© 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. 43468
    Prev
    Next
    INDEX
    Explanations

    viruses or bacteria

    np_max-act · gemini-2.0-flash

    terms related to bacterial infections and their mechanisms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to terms naming or describing pathogens (e.g. “bacterial,” “viral,” “microbial,” etc.), i.e. words signaling infection or pathogen biology.

    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
     tempered
    -0.08
    Seconds
    -0.07
    <size
    -0.07
    输
    -0.07
    Made
    -0.07
    utdown
    -0.07
    ابد
    -0.07
     Arts
    -0.06
     Competition
    -0.06
    .SECONDS
    -0.06
    POSITIVE LOGITS
    =db
    0.08
     bacterial
    0.07
     implied
    0.07
    db
    0.06
    人員
    0.06
    CLASS
    0.06
     첫
    0.06
     suger
    0.06
     услов
    0.06
     worsening
    0.06
    Activations Density 0.007%

    No Known Activations