© 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. 6030
    Prev
    Next
    INDEX
    Explanations

    Limited edition copies

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric expressions—especially edition sizes, quantities, and other digit-based counts.

    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
    Senate
    -0.07
     ACK
    -0.06
    Fire
    -0.06
     beep
    -0.06
     auction
    -0.06
    Collision
    -0.06
     volunteered
    -0.06
    ода
    -0.06
     sep
    -0.06
    conomy
    -0.06
    POSITIVE LOGITS
    .setWidth
    0.07
    dsa
    0.06
    235
    0.06
    repository
    0.06
     Duterte
    0.06
    enerative
    0.06
    ases
    0.06
    .Ordinal
    0.06
     dağ
    0.06
     embar
    0.06
    Activations Density 0.016%

    No Known Activations