© 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. 68383
    Prev
    Next
    INDEX
    Explanations

    code/math

    np_max-act · gemini-2.0-flash

    This neuron never activates on any content tokens—it effectively detects no patterns (i.e., it’s a “dead” neuron).

    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
     unfit
    -0.07
     beware
    -0.06
    olare
    -0.06
    -worthy
    -0.06
     chilly
    -0.06
     filetype
    -0.06
     Tasmania
    -0.06
    ?key
    -0.06
     chuyến
    -0.06
     اک
    -0.06
    POSITIVE LOGITS
    跟
    0.06
     Isl
    0.06
    nof
    0.06
     regulating
    0.06
     
    ↵ 
    ↵
    0.06
     Outstanding
    0.06
    』↵↵
    0.06
    एस
    0.06
    .pol
    0.06
     wenn
    0.06
    Activations Density 0.068%

    No Known Activations