© 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
    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. 92151
    Prev
    Next
    INDEX
    Explanations

    Hexadecimal and numerical data

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (decimal numbers with fractional parts).

    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
    .sound
    -0.07
    اسر
    -0.07
    Showing
    -0.06
     Ny
    -0.06
    quality
    -0.06
     Однак
    -0.06
    Pooling
    -0.06
    Recent
    -0.06
    ////////////////////////////////////////////////////////
    -0.06
    居民
    -0.06
    POSITIVE LOGITS
     munch
    0.07
     compromises
    0.07
     gaz
    0.06
    AREA
    0.06
    cern
    0.06
    369
    0.06
    ✔
    0.06
     decltype
    0.06
     impeccable
    0.06
     casa
    0.06
    Activations Density 0.001%

    No Known Activations