© 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. 110605
    Prev
    Next
    INDEX
    Explanations

    total

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that signal “how many”-style questions about counting or totals.

    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
    .myapplication
    -0.07
     sanitizer
    -0.07
     살
    -0.06
     Shepard
    -0.06
     sınıf
    -0.06
     setattr
    -0.06
     Pepper
    -0.06
     defeated
    -0.06
    resizing
    -0.06
     artış
    -0.06
    POSITIVE LOGITS
    真是
    0.06
     profile
    0.06
    лика
    0.06
    lightly
    0.06
    最后
    0.06
    ksi
    0.06
    umbling
    0.06
    ibble
    0.06
    oggle
    0.06
    زية
    0.06
    Activations Density 0.009%

    No Known Activations