© 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. 90874
    Prev
    Next
    INDEX
    Explanations

    choices and options

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical expressions—especially decimal numbers, percentages, measurements, and similar numeric tokens.

    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
    CACHE
    -0.07
     схем
    -0.07
    .toString
    -0.06
    avg
    -0.06
     आपक
    -0.06
    .fn
    -0.06
    谷
    -0.06
     мыш
    -0.06
    INTR
    -0.06
     mdb
    -0.06
    POSITIVE LOGITS
     eight
    0.06
     additives
    0.06
     luyện
    0.06
     eta
    0.06
    steady
    0.06
    codile
    0.06
    信
    0.06
    Tokenizer
    0.06
    Ö
    0.06
    unei
    0.05
    Activations Density 0.249%

    No Known Activations