© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 918
    Prev
    Next
    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash

    The neuron fires on the floating‐point version numbers (e.g. “2.98…”, “3.04…”) in license boilerplate.

    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
     prol
    -0.06
     pair
    -0.06
     mailing
    -0.06
     subcontract
    -0.06
     přátel
    -0.06
    Assembly
    -0.06
     Reason
    -0.06
     seventeen
    -0.06
     "-"
    -0.06
     Various
    -0.06
    POSITIVE LOGITS
    bert
    0.08
    skins
    0.07
    潜
    0.07
     فوتبال
    0.07
     الخ
    0.07
    every
    0.06
    сих
    0.06
    еление
    0.06
    ffective
    0.06
    ерт
    0.06
    Activations Density 0.002%

    No Known Activations