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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126770
    Prev
    Next
    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron responds to decimal numeric values (especially floating‐point numbers) in XML attribute specifications.

    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
    underscore
    -0.07
     shuffle
    -0.07
    660
    -0.06
    asInstanceOf
    -0.06
     Hide
    -0.06
     NFL
    -0.06
    inecraft
    -0.06
    ulate
    -0.06
    rium
    -0.06
     granny
    -0.06
    POSITIVE LOGITS
    给
    0.07
     genetics
    0.07
    棒
    0.06
    ้ำ
    0.06
     مرگ
    0.06
     JsonRequest
    0.06
     Mods
    0.06
     шт
    0.06
    уття
    0.06
    瓶
    0.06
    Activations Density 0.003%

    No Known Activations