© 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. 6803
    Prev
    Next
    INDEX
    Explanations

    antibiotics

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of specific antibiotics (drug names) and related susceptibility/resistance data.

    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
    .sc
    -0.06
     Evaluation
    -0.06
     Matthias
    -0.06
    โก
    -0.06
     FF
    -0.06
     L
    -0.06
     मज
    -0.06
     niž
    -0.06
     яб
    -0.06
     vaccination
    -0.06
    POSITIVE LOGITS
    LPARAM
    0.06
    	g
    0.06
    	ctx
    0.06
    !")↵
    0.06
     kern
    0.06
    /g
    0.06
     dun
    0.06
     sidewalks
    0.06
    irler
    0.06
     isteyen
    0.06
    Activations Density 0.008%

    No Known Activations