© 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. 128416
    Prev
    Next
    INDEX
    Explanations

    analogy

    np_max-act · gemini-2.0-flash

    analogies that clarify complex concepts in deep learning, particularly related to transformer architectures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates when the text includes a request for or use of analogies (e.g. “analogy,” “analogies,” “visual analogy”).

    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
    oppable
    -0.08
    Ryan
    -0.07
    Forest
    -0.07
    ستگی
    -0.06
    Associate
    -0.06
    Executing
    -0.06
     fold
    -0.06
    .iso
    -0.06
     miscellaneous
    -0.06
    .ot
    -0.06
    POSITIVE LOGITS
     Canberra
    0.07
    pf
    0.07
    [vertex
    0.07
     notable
    0.07
    >{{
    0.07
     setText
    0.06
    anoi
    0.06
    setContent
    0.06
     generously
    0.06
    (packet
    0.06
    Activations Density 0.053%

    No Known Activations