© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110704
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron responds to technical biochemical terms—especially multi‐part substrate or enzyme names (often hyphenated) and kinetics parameters like “Km.”

    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
    aghetti
    -0.06
     Hooks
    -0.06
    cellent
    -0.06
     gradient
    -0.06
     arenas
    -0.06
    ahrungen
    -0.06
     sheriff
    -0.06
     bites
    -0.06
    .Comm
    -0.06
     Elena
    -0.06
    POSITIVE LOGITS
     Permission
    0.07
     odpowied
    0.07
     명
    0.07
    ----------</
    0.07
     _____
    0.06
    ánu
    0.06
               ↵
    0.06
    .security
    0.06
     मस
    0.06
     Společ
    0.06
    Activations Density 0.019%

    No Known Activations