© 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. 56041
    Prev
    Next
    INDEX
    Explanations

    Solving equations

    np_max-act · gemini-2.0-flash

    This neuron detects mathematical equation fragments—especially numeric coefficients, variables, and LaTeX-style math notation.

    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
    (Icons
    -0.09
    щее
    -0.07
     пацієн
    -0.06
    .ser
    -0.06
     میکن
    -0.06
    inis
    -0.06
    ordinate
    -0.06
    sticks
    -0.06
    _UNIX
    -0.06
     第
    -0.06
    POSITIVE LOGITS
    <li
    0.08
    _VM
    0.07
    _ads
    0.06
    :**
    0.06
     İh
    0.06
    .githubusercontent
    0.06
    mostly
    0.06
    _FB
    0.06
     Enumerable
    0.06
    _dimension
    0.06
    Activations Density 0.010%

    No Known Activations