© 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. 15-RESID-POST-AA
    11. 58436
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    This neuron detects tokens from structured machine-readable plan/DDL/JSON blocks and related metadata (e.g., words like "plan", "statement", "ddl", "properties", "stream", "topic").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ступ
    -0.08
     aquel
    -0.07
    tak
    -0.07
    тар
    -0.07
    ilerek
    -0.07
     stigma
    -0.06
    .AspNetCore
    -0.06
    这个
    -0.06
    ạp
    -0.06
    iciel
    -0.06
    POSITIVE LOGITS
    ‌انبار
    0.07
     Implements
    0.06
    _machine
    0.06
    plen
    0.06
     Recipe
    0.06
    _Link
    0.06
    creating
    0.06
     MLA
    0.06
        	
↵
    0.05
    ERCHANT
    0.05
    Activations Density 0.000%

    No Known Activations