© 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 EvalsExportsinterp-engineNEWAPI 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. 58701
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash

    The neuron activates on the “state” in the common phrase “state-of-the-art,” i.e. it picks up mentions of “state-of-the-art” facilities or capabilities.

    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
     Casting
    -0.07
    (cc
    -0.07
    col
    -0.06
    -disable
    -0.06
     Older
    -0.06
    ierung
    -0.06
    validate
    -0.06
     Resolver
    -0.06
     treats
    -0.06
    (lock
    -0.06
    POSITIVE LOGITS
    CALE
    0.07
    OMIC
    0.07
    не
    0.06
                                                ↵
    0.06
     »↵↵
    0.06
     verbally
    0.06
     Kentucky
    0.06
     bu
    0.06
     ]↵↵↵
    0.06
     саме
    0.06
    Activations Density 0.004%

    No Known Activations