© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92322
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the CSV “empty‐field” marker—i.e. the literal “,, ” (commas in succession) or comma quoted as an empty field.

    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
    �
    -0.07
    icipants
    -0.06
    aghetti
    -0.06
     workshops
    -0.06
    _web
    -0.06
     bathroom
    -0.06
    KeyCode
    -0.06
     Rosie
    -0.05
     Helsinki
    -0.05
    children
    -0.05
    POSITIVE LOGITS
    .Load
    0.08
    이를
    0.07
    ’ve
    0.07
    	Description
    0.07
               ↵
    0.07
                               ↵
    0.07
    ceiving
    0.07
                                  ↵
    0.07
     Tweets
    0.07
      ↵    ↵
    0.07
    Activations Density 0.027%

    No Known Activations