© 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. 42708
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric literals, especially floating‐point numbers and decimal measurements in the text.

    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
     bro
    -0.07
    label
    -0.07
     Buccane
    -0.06
    eryl
    -0.06
    .delivery
    -0.06
     Laurie
    -0.06
    connection
    -0.06
     کیلومتر
    -0.06
    <Location
    -0.06
    ิลล
    -0.06
    POSITIVE LOGITS
    quires
    0.06
    град
    0.06
    ileged
    0.06
    _native
    0.06
     �
    0.06
    +F
    0.06
     %↵
    0.06
     Speak
    0.06
    adora
    0.05
    /stretch
    0.05
    Activations Density 0.021%

    No Known Activations