© 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
    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. 68410
    Prev
    Next
    INDEX
    Explanations

    medical topics

    np_max-act · gemini-2.0-flash

    medical terms related to serious health conditions.

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

    The neuron activates on the adjective “Massive,” especially when used as a prominent descriptor (e.g., in medical or headline contexts).

    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
     understands
    -0.07
     end
    -0.07
     until
    -0.07
     sung
    -0.07
    行业
    -0.06
     expresses
    -0.06
     воно
    -0.06
     towards
    -0.06
     cyst
    -0.06
    int
    -0.06
    POSITIVE LOGITS
     massive
    0.14
     Massive
    0.12
    assets
    0.08
     massively
    0.08
    assic
    0.08
    ビ
    0.08
    سي
    0.08
    フィ
    0.07
    沃
    0.07
    ebb
    0.07
    Activations Density 0.004%

    No Known Activations