© 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. 109660
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens representing decimal numbers (floating‐point numeric 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
    /fire
    -0.08
    ān
    -0.08
     Safari
    -0.07
     ratt
    -0.07
    .callbacks
    -0.07
    寻
    -0.07
    breaking
    -0.06
     auxiliary
    -0.06
    _join
    -0.06
    -client
    -0.06
    POSITIVE LOGITS
     &#
    0.07
    _FOUND
    0.07
    .Contact
    0.06
    ं
    0.06
     sympathy
    0.06
     司
    0.06
    (single
    0.06
     منها
    0.06
    \<
    0.06
     junit
    0.06
    Activations Density 0.080%

    No Known Activations