© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30602
    Prev
    Next
    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect numeric expressions—especially quantities with decimal values, percentages, dates, and units of time.

    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
     Boston
    -0.07
     Battery
    -0.07
    Date
    -0.06
    Booking
    -0.06
     Aus
    -0.06
    (output
    -0.06
     punishments
    -0.06
    alls
    -0.06
    (argc
    -0.06
    _nv
    -0.06
    POSITIVE LOGITS
     contained
    0.06
    	SDL
    0.06
     označ
    0.06
    Britain
    0.06
     undergoing
    0.06
    ційний
    0.06
     mod
    0.06
    装置
    0.06
    Research
    0.06
    ather
    0.06
    Activations Density 0.009%

    No Known Activations