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. 130671
    Prev
    Next
    INDEX
    Explanations

    violation

    np_max-act · gemini-2.0-flash

    The neuron fires on the term “violation” (typically in legal contexts).

    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
     mutlaka
    -0.06
     Alps
    -0.06
    fc
    -0.06
     catalogs
    -0.06
     Pharmacy
    -0.06
    alsex
    -0.06
    (wallet
    -0.06
    .Getter
    -0.06
    _math
    -0.06
     retract
    -0.06
    POSITIVE LOGITS
    <num
    0.07
    Brit
    0.07
     mongoose
    0.07
    +.
    0.07
    hub
    0.07
    はい
    0.07
     +
    ↵
    0.07
    [];↵↵
    0.07
    ######↵
    0.07
     nối
    0.07
    Activations Density 0.002%

    No Known Activations