© 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. 91414
    Prev
    Next
    INDEX
    Explanations

    latter

    np_max-act · gemini-2.0-flash

    This neuron activates specifically on the word “latter,” i.e. instances of “latter” used to refer back to a preceding item.

    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
    _manage
    -0.08
     GP
    -0.07
    .Do
    -0.07
     analyzes
    -0.07
    ูนย
    -0.07
    tgl
    -0.07
    UGE
    -0.07
     Ana
    -0.07
    bags
    -0.07
     لیگ
    -0.07
    POSITIVE LOGITS
     latter
    0.13
    atter
    0.07
     بوده
    0.07
     typo
    0.07
    Τ
    0.07
     Reaper
    0.07
    der
    0.06
     Latter
    0.06
     GLUT
    0.06
     згод
    0.06
    Activations Density 0.006%

    No Known Activations