© 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
    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. 30423
    Prev
    Next
    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literal tokens—especially floating‐point numbers (including negative decimals) in math expressions.

    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
    нам
    -0.08
    **
    -0.07
     chilly
    -0.06
    _Password
    -0.06
    During
    -0.06
     آباد
    -0.06
    -icons
    -0.06
    /M
    -0.06
    Legendary
    -0.06
     defending
    -0.06
    POSITIVE LOGITS
     strchr
    0.06
    BITS
    0.06
    पत
    0.06
     Peanut
    0.06
    enever
    0.06
     expectations
    0.06
    +',
    0.06
     Dise
    0.06
    _Params
    0.06
    weights
    0.06
    Activations Density 0.002%

    No Known Activations