© 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 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. 56479
    Prev
    Next
    INDEX
    Explanations

    bugs being fixed

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens in answers that report a known bug or issue being fixed (e.g. “bug,” “fixed,” version numbers in a fix announcement).

    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
    annies
    -0.07
    _FORMAT
    -0.07
     Pool
    -0.07
    Center
    -0.06
    declaration
    -0.06
     '.$
    -0.06
    ouble
    -0.06
    ellers
    -0.06
    antz
    -0.06
    ;"><?
    -0.06
    POSITIVE LOGITS
    第四
    0.07
     lạ
    0.07
    lus
    0.07
     اليمن
    0.06
     světa
    0.06
    .Texture
    0.06
    _heads
    0.06
     Shel
    0.06
    serir
    0.06
     يج
    0.06
    Activations Density 0.019%

    No Known Activations