Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129447
    Prev
    Next
    INDEX
    Explanations

    quantum

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the term “quantum,” essentially detecting mentions of quantum computing.

    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
    rep
    -0.07
    .Skin
    -0.07
    ecast
    -0.07
     yolc
    -0.07
    -moving
    -0.06
     Harbor
    -0.06
    Have
    -0.06
    ンジ
    -0.06
    ρί
    -0.06
    660
    -0.06
    POSITIVE LOGITS
     quantum
    0.12
     Quantum
    0.11
    QUERY
    0.07
    ium
    0.07
     engineering
    0.07
    agem
    0.07
     globalization
    0.07
    सन
    0.07
    am
    0.07
    ');
    0.07
    Activations Density 0.005%

    No Known Activations