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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58669
    Prev
    Next
    INDEX
    Explanations

    Email headers

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is identify fragments of email addresses or email header identifiers (usernames, domains, and name parts).

    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
     gelenek
    -0.07
    (cls
    -0.06
    Responder
    -0.06
     threaten
    -0.06
    ambiguous
    -0.06
     Adjustable
    -0.06
    issing
    -0.06
    .decoder
    -0.06
     valves
    -0.06
     Illegal
    -0.06
    POSITIVE LOGITS
     swirl
    0.07
     NOI
    0.06
     khu
    0.06
    共和
    0.06
    <x
    0.06
     ahead
    0.06
    gfx
    0.06
     TODAY
    0.06
     DON
    0.06
     canonical
    0.06
    Activations Density 0.008%

    No Known Activations