© 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. 13902
    Prev
    Next
    INDEX
    Explanations

    logic

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “logic” (and closely related terms like “logic circuits” or “logic functions”) in technical hardware descriptions.

    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
    starter
    -0.07
    fuse
    -0.07
     websites
    -0.07
     Созд
    -0.07
     згад
    -0.07
    [tmp
    -0.06
     pools
    -0.06
     nằm
    -0.06
    .Setup
    -0.06
    _fixture
    -0.06
    POSITIVE LOGITS
     Grape
    0.08
    LLU
    0.07
    _Form
    0.06
    سة
    0.06
     elim
    0.06
    蛋
    0.06
    SED
    0.06
     неприят
    0.06
     tri
    0.06
     secara
    0.06
    Activations Density 0.009%

    No Known Activations