© 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. 126850
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects structural or formatting tokens (e.g., special markup and header identifiers) that delineate the instruction-response context.

    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
     查看
    -0.07
    札
    -0.06
    ╝
    -0.06
    查询
    -0.06
    ocaust
    -0.06
     củ
    -0.06
     startPosition
    -0.06
    َال
    -0.06
    得到
    -0.06
    020
    -0.06
    POSITIVE LOGITS
     Awards
    0.07
     duties
    0.07
    -js
    0.06
    нести
    0.06
     tüket
    0.06
    -l
    0.06
     contents
    0.06
     LJ
    0.06
     MN
    0.06
    цять
    0.06
    Activations Density 0.003%

    No Known Activations