© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29602
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron spikes on user‐posed “how to” or “tell me how to” style requests for step-by-step instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    instructions and code snippets related to programming and deployment in various environments.

    oai_token-act-pair · gpt-4o-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
     tj
    -0.07
    markets
    -0.07
    ha
    -0.06
    ﻟ
    -0.06
    .uc
    -0.06
     EAR
    -0.06
    umph
    -0.06
     Vim
    -0.06
    !\
    -0.06
    -sh
    -0.06
    POSITIVE LOGITS
    ριν
    0.07
    誰
    0.07
     {/*
    0.06
     bronze
    0.06
     čís
    0.06
    itable
    0.06
    ━━
    0.06
     степени
    0.06
     Nicolas
    0.06
     немного
    0.06
    Activations Density 0.084%

    No Known Activations