© 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. 58444
    Prev
    Next
    INDEX
    Explanations

    ours

    np_max-act · gemini-2.0-flash

    This neuron fires on the “Honours” section header (i.e. the word “Honours”) in these footballer biographies.

    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
     Pearce
    -0.07
     �
    -0.06
    _variance
    -0.06
     Stmt
    -0.06
     Geek
    -0.06
    äter
    -0.06
     nhằm
    -0.06
    $date
    -0.06
    114
    -0.06
    泊
    -0.06
    POSITIVE LOGITS
     (\
    0.07
     entity
    0.07
    moz
    0.07
    -Jul
    0.07
    odule
    0.07
     phút
    0.06
     CMD
    0.06
     Entity
    0.06
    .--
    0.06
    ें↵↵
    0.06
    Activations Density 0.001%

    No Known Activations