© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127125
    Prev
    Next
    INDEX
    Explanations

    Liqu

    np_max-act · gemini-2.0-flash

    This neuron activates on names of companies, brands, or other proper‐noun product/organization titles.

    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
     dig
    -0.07
    Conditional
    -0.06
    ounty
    -0.06
     mail
    -0.06
     aid
    -0.06
     části
    -0.06
    ुन
    -0.06
    Intensity
    -0.06
    execution
    -0.06
     password
    -0.06
    POSITIVE LOGITS
     Oakland
    0.07
     мав
    0.06
    Lastly
    0.06
    (snapshot
    0.06
    UNIT
    0.06
     فبراير
    0.06
    _PROVIDER
    0.06
    \Repository
    0.06
    /rc
    0.06
    <Form
    0.06
    Activations Density 0.119%

    No Known Activations