© 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. 38486
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    elements related to food, cooking, and culinary experiences in storytelling.

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

    The neuron detects the numeric quality‐score entry (e.g. the “75” after `"score":`) in the JSON evaluation response.

    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
    效
    -0.07
    枚
    -0.06
    ocker
    -0.06
     Mexico
    -0.06
    OKEN
    -0.06
    VI
    -0.06
    าป
    -0.06
    -0.06
    测试
    -0.06
    لاق
    -0.06
    POSITIVE LOGITS
    ">'.
    0.07
    .word
    0.07
    IMG
    0.06
    literal
    0.06
     enormous
    0.06
    _received
    0.06
    .debian
    0.06
     <*
    0.06
     lỗi
    0.06
     prosperous
    0.06
    Activations Density 0.108%

    No Known Activations