© 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. 7-RESID-POST-AA
    11. 41419
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens (especially multi-digit numbers) in math/problem style text.

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fences
    -0.07
     Grant
    -0.07
    Mac
    -0.06
     má
    -0.06
     Mỹ
    -0.06
     huh
    -0.06
    modules
    -0.06
    mé
    -0.06
     wheels
    -0.06
     Summit
    -0.06
    POSITIVE LOGITS
    ією
    0.06
     Hermione
    0.06
    (true
    0.06
    /constants
    0.06
     g
    0.06
     treasury
    0.05
    imetype
    0.05
     essere
    0.05
    .Compile
    0.05
    Tahoma
    0.05
    Activations Density 0.030%

    No Known Activations