© 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. 91542
    Prev
    Next
    INDEX
    Explanations

    Australia, cats, Ethereum

    np_max-act · gemini-2.0-flash

    references to laws and regulations regarding animal welfare and pet ownership obligations.

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

    The neuron activates on tokens naming specific animal or pet types.

    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
    /misc
    -0.07
    Tickets
    -0.06
    _logo
    -0.06
     scp
    -0.06
    üncü
    -0.06
     mud
    -0.06
    stu
    -0.06
    /activity
    -0.06
    $str
    -0.06
    /y
    -0.06
    POSITIVE LOGITS
     наст
    0.07
     стало
    0.06
    oose
    0.06
    052
    0.06
     آش
    0.06
    اص
    0.06
    _coord
    0.06
    าจารย
    0.06
     Prague
    0.06
     penned
    0.06
    Activations Density 0.158%

    No Known Activations