© 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. 126281
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literals (especially floating-point constants) in code.

    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
     MIL
    -0.07
    joy
    -0.07
    qc
    -0.07
    íte
    -0.07
     Cran
    -0.06
     wealth
    -0.06
    στημα
    -0.06
     PHYS
    -0.06
    alarını
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
    479
    0.06
    _encoding
    0.06
     Prop
    0.06
     wipe
    0.06
    +F
    0.06
     File
    0.06
           
↵
    0.06
    477
    0.06
    _Core
    0.06
    _spacing
    0.06
    Activations Density 0.011%

    No Known Activations