© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 38368
    Prev
    Next
    INDEX
    Explanations

    Formal documents

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens and formal references—years, statute citations, percentages, measurements, and similar numerical or legal‐style figures.

    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
     leakage
    -0.07
     گرفته
    -0.07
     когда
    -0.06
    泳
    -0.06
    しない
    -0.06
    gnore
    -0.06
     noteworthy
    -0.06
    reg
    -0.06
     первую
    -0.06
    acer
    -0.06
    POSITIVE LOGITS
    #SBATCH
    0.07
     inform
    0.07
     patriot
    0.06
    Triple
    0.06
    。しかし
    0.06
    _sql
    0.06
    -
    0.06
    -depend
    0.06
    怎
    0.06
    ор
    0.06
    Activations Density 0.239%

    No Known Activations