© 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
    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. 110632
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting quantitative measurements and statistical values (e.g. numbers with units, ranges, means, percentages).

    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
    analy
    -0.08
     caves
    -0.06
    fov
    -0.06
    Assembly
    -0.06
    odář
    -0.06
     fluids
    -0.06
    kle
    -0.06
     Observable
    -0.06
     implemented
    -0.06
    .java
    -0.06
    POSITIVE LOGITS
    (_('
    0.07
    _extent
    0.07
     görüntü
    0.06
    фіка
    0.06
     mimetype
    0.06
     Arrest
    0.06
     лют
    0.06
     Chennai
    0.06
     یافت
    0.06
    ็จ
    0.06
    Activations Density 0.053%

    No Known Activations