© 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. 8973
    Prev
    Next
    INDEX
    Explanations

    Java Licenses and Packages

    np_max-act · gemini-2.0-flash

    This neuron fires on identifiers of external systems or libraries—i.e. package or framework names (like “nacos,” “hystrix,” “conductor,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    This neuron fires on occurrences of the substring “acos” (as in identifiers or package names like “nacos”).

    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
     Angiosper
    -0.07
     Они
    -0.06
     zeros
    -0.06
    凌
    -0.06
     blk
    -0.06
    अब
    -0.06
    'yi
    -0.06
     पक
    -0.06
    	kfree
    -0.06
    snake
    -0.06
    POSITIVE LOGITS
     possibilities
    0.07
     supplementary
    0.07
     Chavez
    0.07
     resembled
    0.07
     legally
    0.06
     traditions
    0.06
     sailing
    0.06
     OPERATION
    0.06
    рав
    0.06
    -react
    0.06
    Activations Density 0.003%

    No Known Activations