© 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. 764
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to Portuguese measurement‐related variable names (e.g. “pressão” and “temperatura”).

    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
    ってい
    -0.07
    prt
    -0.06
     subdivision
    -0.06
    _std
    -0.06
     McK
    -0.06
    ————————————————
    -0.06
     Boxing
    -0.06
    Stamped
    -0.06
    ゛
    -0.06
     cps
    -0.06
    POSITIVE LOGITS
     mediated
    0.07
    δια
    0.07
    jem
    0.06
     protest
    0.06
    AGE
    0.06
     NVIDIA
    0.06
    (Status
    0.06
    emails
    0.06
     requirement
    0.06
    peater
    0.06
    Activations Density 0.086%

    No Known Activations