© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129700
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on the numeric portion of ordinal markers (e.g. the “11,” “13,” “21,” “22,” “24,” etc. in “11th,” “13th,” “21st,” “22nd,” “24th,” etc.).

    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
    opak
    -0.07
     смерти
    -0.07
     помещ
    -0.06
    ocaust
    -0.06
     Shirt
    -0.06
     memorial
    -0.06
     Nut
    -0.06
    -format
    -0.06
    Mem
    -0.06
    Strength
    -0.06
    POSITIVE LOGITS
    ollectors
    0.07
     transferred
    0.07
     overrides
    0.07
     सच
    0.06
    iii
    0.06
     Vác
    0.06
    384
    0.06
    -Za
    0.06
    elli
    0.06
     Injector
    0.06
    Activations Density 0.028%

    No Known Activations