© 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. 109410
    Prev
    Next
    INDEX
    Explanations

    research papers and code

    np_max-act · gemini-2.0-flash

    This neuron activates on sequences of tokens forming research model or paper title acronyms (like “Seg ViT: Semantic Segmentation with Plain Vision Transformers”).

    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
     cryptographic
    -0.07
     meydana
    -0.06
    FIXME
    -0.06
     selfies
    -0.06
     kendini
    -0.06
     충
    -0.06
     المف
    -0.06
     DataSet
    -0.06
    ยก
    -0.06
     اختص
    -0.06
    POSITIVE LOGITS
     Hà
    0.07
     Units
    0.07
     Presents
    0.07
    ανου
    0.06
     Long
    0.06
    ราย
    0.06
    251
    0.06
    .Sprintf
    0.06
     Radical
    0.06
     Problems
    0.06
    Activations Density 0.039%

    No Known Activations