© 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. 92028
    Prev
    Next
    INDEX
    Explanations

    ap

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of β-lactamase antibiotic-resistance enzymes (e.g. ESBLs and carbapenemases).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phrases related to antibiotic resistance and microbial infections.

    oai_token-act-pair · gpt-4o-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
    ados
    -0.07
    ado
    -0.07
     Voor
    -0.06
     midpoint
    -0.06
    ylinder
    -0.06
    ADE
    -0.06
     stranded
    -0.06
    ział
    -0.06
    ADO
    -0.06
     Miles
    -0.06
    POSITIVE LOGITS
    .dsl
    0.08
    unos
    0.07
    creat
    0.07
    ợ
    0.06
     vowed
    0.06
    ẹ
    0.06
    terraform
    0.06
    >{{
    0.06
    ([^
    0.06
    well
    0.06
    Activations Density 0.002%

    No Known Activations