© 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. 13936
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals with decimal points (floating-point numbers).

    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
     Lotus
    -0.07
    .TIME
    -0.06
     thief
    -0.06
    Ted
    -0.06
     guid
    -0.06
     combustion
    -0.06
    Within
    -0.06
     đương
    -0.06
    スター
    -0.06
     GPL
    -0.06
    POSITIVE LOGITS
    =*/
    0.08
     kval
    0.07
    .Serve
    0.07
    诚
    0.06
    onomous
    0.06
     :-↵
    0.06
    neh
    0.06
     Hamm
    0.06
     확인
    0.06
     quir
    0.06
    Activations Density 0.004%

    No Known Activations