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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 129406
    Prev
    Next
    INDEX
    Explanations

    scientific species names

    np_max-act · gemini-2.0-flash

    This neuron activates on Latin taxonomic names of biological species (e.g., genus and species terms).

    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
    orderby
    -0.07
     hypert
    -0.06
    iyordu
    -0.06
    iferay
    -0.06
    Sector
    -0.06
    /perl
    -0.06
    .Handled
    -0.06
    (state
    -0.06
     зем
    -0.06
     functionName
    -0.06
    POSITIVE LOGITS
     فار
    0.07
     �
    0.06
    )。
    0.06
    @
    0.06
     数
    0.06
    UIAlertAction
    0.06
     yasak
    0.06
    wise
    0.06
     Pieces
    0.06
    τι
    0.06
    Activations Density 0.014%

    No Known Activations