© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91271
    Prev
    Next
    INDEX
    Explanations

    cross

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing plant‐breeding operations—especially terms like “cross,” “breeding,” “hybrid,” “seed,” and similar words indicating crossing or pollination events.

    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
     payment
    -0.07
    (pk
    -0.06
    .xr
    -0.06
     enemies
    -0.06
     NEWS
    -0.06
    ([]);↵↵
    -0.06
     Văn
    -0.06
    영상
    -0.06
     Razor
    -0.06
     평균
    -0.06
    POSITIVE LOGITS
    ového
    0.07
     italiano
    0.07
     Controlled
    0.06
     duplicated
    0.06
    ęp
    0.06
    auen
    0.06
     krás
    0.06
     Continental
    0.06
    Activated
    0.06
     sexle
    0.06
    Activations Density 0.005%

    No Known Activations