Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85352
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron detects the Internet Explorer compatibility declaration (the “IE=…“ value) in an HTML X-UA-Compatible meta tag.

    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
     Doll
    -0.07
    、大
    -0.07
     maneuvers
    -0.06
     лише
    -0.06
     Cair
    -0.06
    かない
    -0.06
     IGN
    -0.06
     Ayrıca
    -0.06
    wner
    -0.06
     heyec
    -0.06
    POSITIVE LOGITS
    csrf
    0.07
    "She
    0.07
     Developing
    0.06
    filepath
    0.06
      ↵    ↵
    0.06
     adopting
    0.06
     jit
    0.06
    性
    0.06
     bron
    0.06
     accountable
    0.06
    Activations Density 0.001%

    No Known Activations