© 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. 54466
    Prev
    Next
    INDEX
    Explanations

    Something going wrong

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions of things going awry or failing—particularly on mentions like “went wrong,” “had gone wrong,” and similar error/failure phrases.

    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
     wavelength
    -0.06
    iв
    -0.06
     آهنگ
    -0.06
     Curse
    -0.06
     Sonuç
    -0.06
     microseconds
    -0.06
     Ta
    -0.06
    (Command
    -0.06
    庄
    -0.06
    ousands
    -0.06
    POSITIVE LOGITS
    ूछ
    0.07
     disag
    0.06
     emerg
    0.06
    implode
    0.06
     Arial
    0.06
     rel
    0.06
    Qual
    0.06
    >>>(
    0.06
    masına
    0.06
    ؟↵
    0.06
    Activations Density 0.043%

    No Known Activations