© 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. 6287
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric data tokens—especially numbers and decimals (e.g. concentration values, measurement figures) in the scientific text.

    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
    tot
    -0.06
    igail
    -0.06
     mant
    -0.06
     MASK
    -0.06
     MIX
    -0.06
     Normally
    -0.06
    _compress
    -0.05
    stands
    -0.05
     ケ
    -0.05
    _skb
    -0.05
    POSITIVE LOGITS
    _subplot
    0.07
    imité
    0.07
    ]])↵↵
    0.06
    (colors
    0.06
     전국
    0.06
    SnackBar
    0.06
     mainScreen
    0.06
    ")));↵↵
    0.06
    [class
    0.06
    eming
    0.06
    Activations Density 0.137%

    No Known Activations