© 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. 92196
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    scientific terminology related to structure and chemical compounds.

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

    The neuron is keyed to the “#” tokens that mark section or heading labels in the text.

    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
    	ent
    -0.07
     apo
    -0.07
    410
    -0.07
    .scenes
    -0.07
    .sa
    -0.07
    /version
    -0.07
    쓰
    -0.07
     contempor
    -0.06
     다음과
    -0.06
     uptime
    -0.06
    POSITIVE LOGITS
     accountant
    0.06
     donations
    0.06
    „M
    0.06
     theories
    0.06
    riers
    0.06
    //{↵
    0.06
    ">'↵
    0.06
    祝
    0.05
     suggestions
    0.05
     сест
    0.05
    Activations Density 0.001%

    No Known Activations