© 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. 783
    Prev
    Next
    INDEX
    Explanations

    reflect

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the “reflect” identifier (i.e. uses of Go’s reflection package).

    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
    clude
    -0.06
    ont
    -0.06
     Cou
    -0.06
     strains
    -0.06
    nod
    -0.06
     mog
    -0.06
     stained
    -0.06
    Spec
    -0.06
     Coord
    -0.06
     dedication
    -0.06
    POSITIVE LOGITS
    richt
    0.07
    reflect
    0.07
     elektronik
    0.06
    /assert
    0.06
    addafi
    0.06
     πολύ
    0.06
    ніш
    0.06
    tober
    0.06
    alış
    0.06
    ;}
↵
    0.06
    Activations Density 0.000%

    No Known Activations