© 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
    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. 6093
    Prev
    Next
    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on occurrences of the word “Energy.”

    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
     skip
    -0.08
    (slice
    -0.07
    14
    -0.07
    113
    -0.07
     března
    -0.07
     chute
    -0.07
     uphold
    -0.07
    iffin
    -0.07
     Chap
    -0.07
    19
    -0.07
    POSITIVE LOGITS
     energy
    0.17
     Energy
    0.16
    Energy
    0.13
    energy
    0.12
     energies
    0.11
    -energy
    0.11
     ENERGY
    0.11
     energ
    0.10
    .energy
    0.10
     Energ
    0.10
    Activations Density 0.029%

    No Known Activations