© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110217
    Prev
    Next
    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash

    terms related to programming and software development.

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

    This neuron detects discourse-level transition phrases or clause openers (e.g. “Side note:”, “To me,” “One of,” “Why is,” etc.).

    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
     Ltd
    -0.07
     LLC
    -0.06
    std
    -0.06
    amarin
    -0.06
    ilian
    -0.06
    ellij
    -0.06
     detriment
    -0.06
     เน
    -0.06
     rocker
    -0.06
     snapchat
    -0.06
    POSITIVE LOGITS
    ===============↵
    0.07
     propre
    0.06
     mechanical
    0.06
     Targets
    0.06
    /lab
    0.06
    則
    0.06
     《
    0.06
    /mm
    0.06
    ひと
    0.06
     nurse
    0.06
    Activations Density 0.655%

    No Known Activations