© 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. 91427
    Prev
    Next
    INDEX
    Explanations

    Regression models

    np_max-act · gemini-2.0-flash

    definitions and explanations related to neural language models.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron lightly activates on technical terms describing model operations or components—words like “enc(oder),” “predicting,” or “sequence.”

    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
    adeon
    -0.08
    .$$
    -0.07
    (goal
    -0.06
    kemiz
    -0.06
    opencv
    -0.06
    集中
    -0.06
    Device
    -0.06
     روسی
    -0.06
    La
    -0.06
     conform
    -0.06
    POSITIVE LOGITS
    -age
    0.06
    َال
    0.06
    リーズ
    0.06
    仁
    0.06
    ามารถ
    0.06
    援
    0.06
     wear
    0.06
     strengthened
    0.06
    irq
    0.06
    瑞
    0.06
    Activations Density 0.013%

    No Known Activations