© 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. 37989
    Prev
    Next
    INDEX
    Explanations

    decide

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to making a decision (e.g., “decision,” “deciding,” “decide”).

    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
    496
    -0.07
     Maurice
    -0.07
     Mushroom
    -0.07
     employs
    -0.07
    Frequency
    -0.06
     fullName
    -0.06
     Foster
    -0.06
     Eph
    -0.06
    Hyper
    -0.06
     mushrooms
    -0.06
    POSITIVE LOGITS
     decide
    0.16
     decided
    0.15
     deciding
    0.14
     decides
    0.14
     Decide
    0.13
     decisive
    0.10
     undecided
    0.10
     decisions
    0.09
    ecided
    0.08
    决定
    0.08
    Activations Density 0.038%

    No Known Activations