© 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. 43071
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash

    The neuron fires on single‐letter variable names (like j, p, r, s, etc.) when they appear in algebraic/exponentiation contexts (e.g. as bases or divisors in power or division expressions).

    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
    enda
    -0.07
    оло
    -0.06
    ANGO
    -0.06
    計
    -0.06
    Ch
    -0.06
    -chat
    -0.06
    ﺔ
    -0.06
    azine
    -0.06
     Rope
    -0.06
    _value
    -0.06
    POSITIVE LOGITS
     leicht
    0.06
    (PHP
    0.06
    ่ะ
    0.06
    VF
    0.06
     incorporation
    0.06
    のは
    0.06
     různých
    0.06
     kp
    0.06
     отримання
    0.06
    //**↵
    0.06
    Activations Density 0.003%

    No Known Activations