© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124895
    Prev
    Next
    INDEX
    Explanations

    academic paper citations

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric and alphanumeric identifiers—things like reference numbers, section or DOI codes, and placeholder names containing digits.

    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
     Footer
    -0.07
     submissive
    -0.06
    uyền
    -0.06
     komb
    -0.06
     Recovery
    -0.06
    uml
    -0.06
    pe
    -0.06
    umbs
    -0.06
    alis
    -0.06
    放在
    -0.06
    POSITIVE LOGITS
     Bat
    0.06
    (AP
    0.06
     Sark
    0.06
     Бел
    0.06
     SPECIAL
    0.06
    .RED
    0.06
     unity
    0.06
     Django
    0.06
    [vertex
    0.06
    Bit
    0.06
    Activations Density 0.093%

    No Known Activations