© 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. 68635
    Prev
    Next
    INDEX
    Explanations

    operator

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the term “operator,” especially in mathematical or quantum-mechanical contexts.

    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
     termination
    -0.07
     Moreno
    -0.06
    EMU
    -0.06
     confession
    -0.06
     SIN
    -0.06
    S
    -0.06
    explain
    -0.06
     Cunning
    -0.06
     mutating
    -0.06
     Interesting
    -0.06
    POSITIVE LOGITS
    brace
    0.06
    Tooltip
    0.06
    aged
    0.06
     cortisol
    0.06
    spir
    0.06
    $url
    0.06
    ator
    0.06
     duvar
    0.06
    ATOR
    0.06
    pector
    0.06
    Activations Density 0.003%

    No Known Activations