Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91144
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal number tokens—especially those giving X-ray or structural resolution values.

    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
     kinetics
    -0.06
    される
    -0.06
     fragment
    -0.06
     eg
    -0.06
    -cycle
    -0.06
    浦
    -0.06
     Strings
    -0.06
    א
    -0.06
     chaired
    -0.06
    ci
    -0.06
    POSITIVE LOGITS
    _disp
    0.07
    isActive
    0.07
     spooky
    0.06
    Tags
    0.06
    xmin
    0.06
    藍
    0.06
    .contents
    0.06
     фін
    0.06
    _taken
    0.06
    management
    0.06
    Activations Density 0.001%

    No Known Activations