© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash

    The neuron detects English ordinal number suffixes (e.g., “th,” “nd,” “rd”) attached to numerals.

    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
     Fallon
    -0.06
     odio
    -0.06
    you
    -0.06
    ₃
    -0.06
    .isOn
    -0.06
    ison
    -0.06
     Bom
    -0.06
     consequat
    -0.06
    암
    -0.06
     Coc
    -0.06
    POSITIVE LOGITS
    th
    0.15
    elfth
    0.11
    teenth
    0.11
    TH
    0.10
     ninth
    0.09
     nineteenth
    0.09
    eenth
    0.09
     twentieth
    0.09
    ph
    0.09
     eighth
    0.08
    Activations Density 0.021%

    No Known Activations