© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42756
    Prev
    Next
    INDEX
    Explanations

    complicated

    np_max-act · gemini-2.0-flash

    This neuron detects language criticizing complexity or difficulty in prior‐art devices, e.g. words highlighting that something is “complicated,” “inefficient,” or similarly troublesome.

    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
    pipes
    -0.07
     comfy
    -0.06
    بي
    -0.06
     persona
    -0.06
    ensitivity
    -0.06
    ENCHMARK
    -0.06
     "":↵
    -0.06
    Client
    -0.06
    。这
    -0.06
     Glas
    -0.06
    POSITIVE LOGITS
     concluding
    0.07
    .ceil
    0.06
     giả
    0.06
    ้อย
    0.06
    841
    0.06
    .divide
    0.06
     天
    0.06
    .Service
    0.06
    \HttpFoundation
    0.06
    优
    0.06
    Activations Density 0.021%

    No Known Activations