Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41728
    Prev
    Next
    INDEX
    Explanations

    transcription

    np_max-act · gemini-2.0-flash

    technical terms related to software development and security vulnerabilities.

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

    The neuron selectively activates on specialized biomedical terminology, especially words related to blood vessel growth (angiogenesis) and vascular/endothelial biology.

    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
     Yamaha
    -0.07
    قیق
    -0.06
     karış
    -0.06
    仕事
    -0.06
     customers
    -0.06
    过来
    -0.06
    ontology
    -0.06
    زارش
    -0.06
    。\
    -0.06
     vieille
    -0.06
    POSITIVE LOGITS
    LOY
    0.06
     distint
    0.06
    .cam
    0.06
    xaa
    0.06
    .CONT
    0.06
    _KIND
    0.06
    ा↵↵
    0.06
    .Dto
    0.06
    /connection
    0.06
    wayne
    0.06
    Activations Density 0.421%

    No Known Activations