© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 44988
    Prev
    Next
    INDEX
    Explanations

    Types

    np_max-act · gemini-2.0-flash

    issues related to Android project configuration and dependencies.

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

    The neuron activates on numeric literal tokens—especially decimal version numbers and configuration values—in build.gradle files.

    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
     ImageButton
    -0.07
    Esta
    -0.06
     Regression
    -0.06
     Atkins
    -0.06
     Mesh
    -0.06
    ิท
    -0.06
     compost
    -0.06
    abby
    -0.06
     oppressed
    -0.06
    自然
    -0.06
    POSITIVE LOGITS
     xin
    0.08
     nombres
    0.07
    Ord
    0.07
    -с
    0.07
    -binary
    0.07
    /S
    0.06
    Bs
    0.06
    ในว
    0.06
    _learning
    0.06
    _CURRENT
    0.06
    Activations Density 0.000%

    No Known Activations