© 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. 11-RESID-POST-AA
    11. 42786
    Prev
    Next
    INDEX
    Explanations

    Greek mythology

    np_max-act · gemini-2.0-flash

    The neuron fires on multi‐syllabic, capitalized name strings—i.e. proper names of people or places in Greek mythology.

    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
     userInput
    -0.06
     hacked
    -0.06
     أنا
    -0.06
     mach
    -0.06
     impeachment
    -0.06
     国
    -0.06
    \web
    -0.06
     情
    -0.06
     realmente
    -0.06
     Českosloven
    -0.05
    POSITIVE LOGITS
    _CONTEXT
    0.07
    otto
    0.07
     reside
    0.07
     anecd
    0.07
    》的
    0.07
     Chavez
    0.06
     evaluated
    0.06
     Motors
    0.06
    getSize
    0.06
     minecraft
    0.06
    Activations Density 0.014%

    No Known Activations