© 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. 92494
    Prev
    Next
    INDEX
    Explanations

    medical

    np_max-act · gemini-2.0-flash

    This neuron activates on domain-specific key nouns or category labels (e.g. drug or substance names, anatomical sites, dataset/task labels, or event names).

    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
    	Buffer
    -0.06
     Task
    -0.06
    :
↵
    -0.06
    elts
    -0.06
    ़ी
    -0.06
    _DISABLED
    -0.06
     度
    -0.06
    _pins
    -0.06
     IReadOnly
    -0.06
    잖
    -0.05
    POSITIVE LOGITS
     winger
    0.07
     고객
    0.07
    今
    0.07
    ывая
    0.06
     seine
    0.06
     dipped
    0.06
    プラ
    0.06
     وت
    0.06
     Chili
    0.06
     dolar
    0.06
    Activations Density 0.047%

    No Known Activations