© 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. 7105
    Prev
    Next
    INDEX
    Explanations

    literally

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially multi‐digit numbers like years or dates.

    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
    /*****************************************************************************↵
    -0.07
    _Parse
    -0.07
    -index
    -0.07
    .GL
    -0.07
    .Create
    -0.07
    vect
    -0.07
     собой
    -0.06
    .days
    -0.06
     visa
    -0.06
    .Details
    -0.06
    POSITIVE LOGITS
    İL
    0.06
     produkt
    0.06
     SMP
    0.06
     literally
    0.06
    �
    0.06
    方
    0.05
    work
    0.05
     mouths
    0.05
    WORK
    0.05
     rew
    0.05
    Activations Density 0.023%

    No Known Activations