© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58041
    Prev
    Next
    INDEX
    Explanations

    ZF set theory

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting LaTeX‐style uppercase acronyms and symbols for formal set-theoretic or axiomatic systems (e.g. “ZFC,” “CIFS,” “IFS,” “V,” etc.).

    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
    　　　　
    -0.07
     Hastings
    -0.06
    @AllArgsConstructor
    -0.06
    @Resource
    -0.06
    Logout
    -0.06
    pras
    -0.06
     Bulgarian
    -0.06
     Tells
    -0.06
     　 　
    -0.05
    errupt
    -0.05
    POSITIVE LOGITS
    UIAlertAction
    0.07
    \Action
    0.06
    如此
    0.06
     versions
    0.06
     Daha
    0.06
    orta
    0.06
     Ames
    0.06
    uilder
    0.06
    EditingStyle
    0.06
     certs
    0.06
    Activations Density 0.004%

    No Known Activations