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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130472
    Prev
    Next
    INDEX
    Explanations

    Code/Markup

    np_max-act · gemini-2.0-flash

    This neuron detects image‐placeholder tokens (e.g. “IMAGE” inside brackets) in the document.

    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
     Carolina
    -0.06
      	 
    -0.06
    专业
    -0.06
     eta
    -0.06
     ovšem
    -0.06
    .asc
    -0.06
     není
    -0.06
    ioxid
    -0.06
     Hopkins
    -0.06
     isEqual
    -0.06
    POSITIVE LOGITS
    flows
    0.07
     receives
    0.06
     indonesia
    0.06
     números
    0.06
    ymbols
    0.06
    orse
    0.06
     configuration
    0.06
     residue
    0.06
    전
    0.06
     гиб
    0.06
    Activations Density 0.085%

    No Known Activations