© 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. 126791
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric literal tokens representing decimal fractions (i.e. floating-point numbers).

    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
    acci
    -0.06
    .bunifu
    -0.06
     oci
    -0.06
    _ros
    -0.06
     russe
    -0.06
    armac
    -0.06
     LocalDate
    -0.06
    [block
    -0.06
     roi
    -0.06
     weaving
    -0.06
    POSITIVE LOGITS
    .setHeader
    0.07
    Disk
    0.07
     đương
    0.07
    _state
    0.07
    .NEW
    0.06
     Williams
    0.06
     Electric
    0.06
    ับท
    0.06
    려고
    0.06
     Disk
    0.06
    Activations Density 0.007%

    No Known Activations