© 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
    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. 92391
    Prev
    Next
    INDEX
    Explanations

    ially/entially

    np_max-act · gemini-2.0-flash

    This neuron responds to dense bioinformatics and transcriptomics jargon—terms indicating sequencing‐based expression analysis and differential gene expression workflows.

    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
    び
    -0.07
     Thou
    -0.07
    Factor
    -0.06
    .getJSONArray
    -0.06
    zip
    -0.06
    LED
    -0.06
    passed
    -0.06
     quadratic
    -0.06
    Ky
    -0.06
    Colon
    -0.06
    POSITIVE LOGITS
     kvin
    0.07
     >↵↵
    0.07
    /F
    0.06
     ConfigurationManager
    0.06
     +↵↵
    0.06
     Staff
    0.06
     tipping
    0.06
    +'/
    0.06
    detail
    0.06
    bral
    0.06
    Activations Density 0.005%

    No Known Activations