© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126752
    Prev
    Next
    INDEX
    Explanations

    copyright and fair use

    np_max-act · gemini-2.0-flash

    The neuron activates on legal and copyright/fair-use disclaimer language.

    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
     úplně
    -0.06
     hotter
    -0.06
    Recipes
    -0.06
     更
    -0.05
    Campaign
    -0.05
    _LINE
    -0.05
    UDGE
    -0.05
     melted
    -0.05
    Lic
    -0.05
    periments
    -0.05
    POSITIVE LOGITS
     Syracuse
    0.07
     sistemi
    0.07
    compiler
    0.07
     Personally
    0.07
     Joomla
    0.07
     chví
    0.07
    ة
    0.07
     lorsque
    0.07
    _virtual
    0.06
     Tells
    0.06
    Activations Density 0.004%

    No Known Activations