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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 40546
    Prev
    Next
    INDEX
    Explanations

    ail

    np_max-act · gemini-2.0-flash

    The neuron is activated by occurrences of the word “snail” (as in “sea snail”) in species descriptions.

    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
    _PS
    -0.08
    .getById
    -0.07
     �
    -0.07
    ्वत
    -0.06
     Payments
    -0.06
    .turn
    -0.06
     ию
    -0.06
     izin
    -0.06
     Buildings
    -0.06
     pb
    -0.06
    POSITIVE LOGITS
    ERENCE
    0.07
    -drive
    0.06
     أكبر
    0.06
     inclusive
    0.06
     memory
    0.06
    ertia
    0.06
     Candid
    0.06
     click
    0.06
     accompanying
    0.06
     Recovery
    0.06
    Activations Density 0.000%

    No Known Activations