© 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. 90834
    Prev
    Next
    INDEX
    Explanations

    Dates, numbers, reports, and code

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially parts of dates, counts, and other digit sequences.

    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
    (vs
    -0.07
    962
    -0.07
     гре
    -0.07
     Cyc
    -0.07
     pivot
    -0.07
     outweigh
    -0.07
    "github
    -0.06
    を開
    -0.06
    ').↵
    -0.06
     Dalton
    -0.06
    POSITIVE LOGITS
     verifica
    0.07
     CV
    0.06
    าจ
    0.06
    unfinished
    0.06
     ao
    0.06
    Рё
    0.06
     financier
    0.06
     els
    0.06
     Imam
    0.06
     selected
    0.06
    Activations Density 0.178%

    No Known Activations