© 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
    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. 127051
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    permissions and licensing information related to software.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on the key permission-granting verbs (e.g. “copy,” “modify,” “distribute,” “and”) in open-source license texts.

    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
    setImage
    -0.08
    AndWait
    -0.06
     skiing
    -0.06
    ension
    -0.06
    _services
    -0.06
     exchanged
    -0.06
    	of
    -0.06
    ushi
    -0.06
    Ticker
    -0.06
    acement
    -0.06
    POSITIVE LOGITS
     COOKIE
    0.08
     fantast
    0.07
     Inn
    0.06
    PropertyChanged
    0.06
    [++
    0.06
    CNT
    0.06
    ़न
    0.06
    .onOptionsItemSelected
    0.06
     ανα
    0.06
    primitive
    0.06
    Activations Density 0.001%

    No Known Activations