© 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. 6945
    Prev
    Next
    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “distributed” (as in “distributed under the License”) 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
     getIntent
    -0.07
    ing
    -0.07
    ons
    -0.06
    Cos
    -0.06
     ello
    -0.06
    ajas
    -0.06
     obsolete
    -0.06
     hut
    -0.06
    770
    -0.06
     diseases
    -0.06
    POSITIVE LOGITS
     Prospect
    0.07
     измен
    0.06
    طه
    0.06
    %.
    0.06
    %"
    0.06
     wł
    0.06
     мас
    0.06
    (distance
    0.06
    uitar
    0.06
     Falling
    0.06
    Activations Density 0.001%

    No Known Activations