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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128668
    Prev
    Next
    INDEX
    Explanations

    with to

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (decimal numbers) in the 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
     routed
    -0.06
    ии
    -0.06
     cured
    -0.06
    昇
    -0.06
    _cells
    -0.06
    بالإنجليزية
    -0.06
    (((
    -0.06
    egal
    -0.06
     أحمد
    -0.06
     shoot
    -0.06
    POSITIVE LOGITS
    uly
    0.07
    trial
    0.06
     intrinsic
    0.06
    klär
    0.06
    exceptions
    0.06
     penned
    0.06
    -update
    0.05
     luk
    0.05
    .pack
    0.05
    uyordu
    0.05
    Activations Density 0.015%

    No Known Activations