© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 1624
    Prev
    Next
    INDEX
    Explanations

    Sylv

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the "Sylv" name root (tokens starting with the substring "Sylv").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quận
    -0.06
     MYSQL
    -0.06
     counters
    -0.06
     Oc
    -0.06
     　 　 　
    -0.06
    něž
    -0.06
    (paren
    -0.06
     Німеч
    -0.06
     Akron
    -0.06
     attempted
    -0.06
    POSITIVE LOGITS
    可能
    0.07
     Oval
    0.07
    víc
    0.07
    pile
    0.07
     olive
    0.07
     		↵
    0.06
     단
    0.06
    _SLAVE
    0.06
    ible
    0.06
     representative
    0.06
    Activations Density 0.013%

    No Known Activations