© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128341
    Prev
    Next
    INDEX
    Explanations

    Encrypt

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens referring to SSL/TLS certificate operations, especially mentions of “cert”, “encrypt”, “Let’s Encrypt”, “SSL”, and related certificate‐management terms.

    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
     Tomb
    -0.07
     models
    -0.07
    姐
    -0.06
     phenomenon
    -0.06
     MODEL
    -0.06
     Goldberg
    -0.06
     dương
    -0.06
    Paper
    -0.06
     handles
    -0.06
    (state
    -0.06
    POSITIVE LOGITS
     Environmental
    0.07
    European
    0.06
    .logger
    0.06
     Dun
    0.06
    ‐‐
    0.06
     arg
    0.06
    .getProperty
    0.06
    き
    0.06
    compress
    0.06
    .awt
    0.06
    Activations Density 0.006%

    No Known Activations