© 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
    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. 8789
    Prev
    Next
    INDEX
    Explanations

    Insect classification

    np_max-act · gemini-2.0-flash

    This neuron detects Latin scientific names or taxonomic labels (e.g., genus, species, family) in the text.

    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
    service
    -0.07
    ]=]
    -0.07
    leston
    -0.06
    ater
    -0.06
    }','
    -0.06
    CLR
    -0.06
    hta
    -0.06
    ,z
    -0.06
     milf
    -0.06
     поэтому
    -0.06
    POSITIVE LOGITS
     WLAN
    0.07
    :';↵
    0.06
     Muss
    0.06
     Çev
    0.06
     ")
    ↵
    0.06
    名称
    0.06
     neh
    0.06
     Glyph
    0.06
    рощ
    0.06
    .Post
    0.06
    Activations Density 0.004%

    No Known Activations