© 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. 124843
    Prev
    Next
    INDEX
    Explanations

    Code/file paths

    np_max-act · gemini-2.0-flash

    elements or structures within code that pertain to data types and definitions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on numeric tokens containing decimal points (i.e. floating-point numbers).

    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
    (li
    -0.06
    _ui
    -0.06
    belt
    -0.06
    umar
    -0.06
    cest
    -0.06
     Stadium
    -0.06
    enderror
    -0.05
    BE
    -0.05
    _callbacks
    -0.05
    ?>"><
    -0.05
    POSITIVE LOGITS
    Stick
    0.07
     herald
    0.07
     stě
    0.07
     distancing
    0.07
     exile
    0.07
    _gp
    0.06
     vita
    0.06
    γραφ
    0.06
     clinics
    0.06
    下
    0.06
    Activations Density 0.159%

    No Known Activations