© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44570
    Prev
    Next
    INDEX
    Explanations

    increase in number

    np_max-act · gemini-2.0-flash

    scientific terminology related to medical conditions, particularly infections.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects verbs that describe microbial or cellular growth and reproduction (e.g., multiply, grow, propagate).

    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
    _into
    -0.07
    роничес
    -0.07
    nesia
    -0.07
    279
    -0.06
    TestingModule
    -0.06
     मत
    -0.06
     horr
    -0.06
     Німеч
    -0.06
     circles
    -0.06
     asyncio
    -0.06
    POSITIVE LOGITS
    "They
    0.07
     unparalleled
    0.06
    	comment
    0.06
     Pam
    0.06
    ected
    0.06
     затем
    0.06
    .Repository
    0.06
    (Main
    0.06
     سپس
    0.06
    (str
    0.06
    Activations Density 0.025%

    No Known Activations